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. 6385
    Prev
    Next
    INDEX
    Explanations

    phrases related to policy discussions and social issues

    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
    eseorang
    -0.42
     currently
    -0.32
    cha
    -0.29
     pratica
    -0.28
     dich
    -0.27
     aforementioned
    -0.27
     previously
    -0.27
     sama
    -0.27
     quotation
    -0.27
    Vad
    -0.26
    POSITIVE LOGITS
    endphp
    0.80
    rungsseite
    0.77
    ftagPool
    0.75
    TypedDataSet
    0.75
     nahilalakip
    0.71
    tagHelperRunner
    0.71
    windowFixed
    0.71
    󠁣
    0.70
    __':
    0.69
     Exacts
    0.69
    Activations Density 0.211%

    No Known Activations