© 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. 18-GEMMASCOPE-RES-16K
    11. 1707
    Prev
    Next
    INDEX
    Explanations

    concepts related to evaluation or feedback

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

    reasoning or discovery

    np_acts-logits-general · gemini-2.0-flash

    legal or investigative terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.59
    WriteAttribute
    -0.56
    ]--;
    -0.56
    weds
    -0.55
    ]));
    -0.54
     jspb
    -0.53
    rawDesc
    -0.52
    dicos
    -0.51
     seu
    -0.51
    />
    -0.50
    POSITIVE LOGITS
     بيها
    0.67
     Catawiki
    0.64
    เอง
    0.61
    MigrationBuilder
    0.56
    曖昧さ回避
    0.55
     sendiri
    0.54
    ographiques
    0.54
    IntoConstraints
    0.53
     toolkit
    0.53
     toolbox
    0.53
    Activations Density 0.852%

    No Known Activations