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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 11095
    Prev
    Next
    INDEX
    Explanations

    instances of actions related to motivation and decision-making

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

    Sentences about similarity or comparison

    np_acts-logits-general · gemini-2.0-flash

    same, similar, likewise

    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
    //
    -0.57
    colha
    -0.53
     通販
    -0.52
    TargetException
    -0.50
    SequentialGroup
    -0.47
    󠁴
    -0.43
    multer
    -0.42
    deltaTime
    -0.42
    etro
    -0.42
     CascadeType
    -0.42
    POSITIVE LOGITS
     same
    3.73
    same
    3.67
    Same
    3.53
     similar
    3.36
     Same
    3.25
     similarly
    3.13
    similar
    3.05
    Similarly
    2.93
    Similar
    2.92
    SAME
    2.85
    Activations Density 2.074%

    No Known Activations