Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 15749
    Prev
    Next
    INDEX
    Explanations

    actions involving physical interactions or movements between objects and people

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

    Immediately precedes "on" or "onto"

    np_acts-logits-general · gemini-2.0-flash

    on or onto the

    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
    jsdelivr
    -0.53
    arrings
    -0.47
     lisäksi
    -0.46
    τερα
    -0.46
    5
    -0.44
    きは
    -0.44
       
    -0.43
    院长
    -0.43
    (
    -0.43
    Tang
    -0.42
    POSITIVE LOGITS
    principalColumn
    0.83
     snippetHide
    0.81
    expandindo
    0.79
     ModelExpression
    0.75
    MessageOf
    0.72
     فريبيس
    0.70
    SharedCtor
    0.70
    uxxxx
    0.66
     ExecuteAsync
    0.66
    VersionUID
    0.66
    Activations Density 0.194%

    No Known Activations