© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14664
    Prev
    Next
    INDEX
    Explanations

    positive descriptors of experiences in an outdoor setting.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming code snippets with elements of uncertainty.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    prefixes and prepositions in Slavic languages, particularly those starting with "po-" or related to movement/direction.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    "po" or "по" in different languages

    np_acts-logits-general · gemini-2.0-flash

    по несколько, second motorcycle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.76
    dengar
    -0.66
    этому
    -0.66
    ResumeLayout
    -0.65
     contextLoads
    -0.61
    protoimpl
    -0.59
    NGC
    -0.58
    BaseActivity
    -0.58
     Autorizaciones
    -0.57
     italienne
    -0.56
    POSITIVE LOGITS
    WireFormatLite
    0.54
     IBOutlet
    0.53
    安
    0.52
     मिल
    0.51
    ArgsConstructor
    0.49
    erunner
    0.48
     Rukh
    0.48
     /\.
    0.47
     comple
    0.46
     MonoBehaviour
    0.46
    Activations Density 0.013%

    No Known Activations