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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17-GEMMASCOPE-RES-16K
    6. 5873
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups that are not part of the main focus, often described collectively as "others"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Miy
    -0.60
     {_
    -0.56
    strona
    -0.55
    indle
    -0.55
    abatic
    -0.54
    gun
    -0.53
    StringTo
    -0.53
    siri
    -0.53
    Columb
    -0.52
    axial
    -0.52
    POSITIVE LOGITS
    InitVars
    0.93
    Portail
    0.79
    انيف
    0.77
    Hauptartikel
    0.72
     виправивши
    0.70
     ressort
    0.69
     ExecuteAsync
    0.69
     дописавши
    0.69
    mybatisplus
    0.68
     Ferner
    0.68
    Activations Density 0.082%

    No Known Activations