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 - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 785
    Prev
    Next
    INDEX
    Explanations

    phrases related to official statements or announcements

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

    foreign language emoticons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputBorder
    -0.80
    SequentialGroup
    -0.80
    AndEndTag
    -0.76
    下载附件
    -0.75
     Autorisations
    -0.74
    IsMutable
    -0.73
    SharedDtor
    -0.73
     oprot
    -0.70
    pexpr
    -0.69
    findpost
    -0.68
    POSITIVE LOGITS
     Unterhaltung
    0.36
     comunicaciones
    0.35
     навчання
    0.35
     löytyy
    0.34
     kväll
    0.33
    ๆ
    0.32
     connaissances
    0.31
     vorbei
    0.31
     Hilfe
    0.31
     Annahme
    0.31
    Activations Density 0.038%

    No Known Activations