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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2138
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes and processes within an organizational or legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Freien
    -0.38
    ,
    -0.38
     kuitenkin
    -0.37
     revanche
    -0.36
     Nación
    -0.33
     billeder
    -0.32
     Kelurahan
    -0.32
     Meksika
    -0.31
     Dinamarca
    -0.31
    gende
    -0.31
    POSITIVE LOGITS
    rungsseite
    0.79
    TagMode
    0.79
     FetchType
    0.79
    tagHelperRunner
    0.75
    onOptions
    0.73
     Normdatei
    0.72
     surla
    0.72
     CURIAM
    0.68
    المناصب
    0.66
    省市镇
    0.66
    Activations Density 1.132%

    No Known Activations