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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 6186
    Prev
    Next
    INDEX
    Explanations

    actions related to communication and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
     geworden
    -0.50
    گز
    -0.49
     to
    -0.47
    sepeda
    -0.46
     diketahui
    -0.43
    gantung
    -0.43
    maksud
    -0.42
     Es
    -0.42
    .
    -0.42
     käs
    -0.42
    POSITIVE LOGITS
     nahilalakip
    0.88
    HtmlAttribute
    0.86
     tartalomajánló
    0.83
    contentLoaded
    0.77
     Theſe
    0.76
     myſelf
    0.76
    rawDesc
    0.74
     ―――――
    0.72
    InjectAttribute
    0.71
     ProtoMessage
    0.71
    Activations Density 0.101%

    No Known Activations