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. 12-GEMMASCOPE-RES-16K
    6. 5722
    Prev
    Next
    INDEX
    Explanations

    details about the features and condition of physical objects, particularly vehicles and buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.56
    CreateIndex
    -0.53
     שוליים
    -0.52
     quelle
    -0.52
     يتيمه
    -0.51
    脚注の使い方
    -0.50
     financières
    -0.50
    RetentionPolicy
    -0.50
    OGND
    -0.49
     sede
    -0.49
    POSITIVE LOGITS
    GrantedAuthority
    0.60
    følgelig
    0.59
    PreferredItem
    0.57
    CloseOperation
    0.57
    djangoproject
    0.57
     Juga
    0.56
    }}]{
    0.55
     /\.(
    0.54
    $_['
    0.53
    tuur
    0.53
    Activations Density 0.197%

    No Known Activations