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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-131K
    6. 22370
    Prev
    Next
    INDEX
    Explanations

    references to British culture or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    executeUpdate
    -0.59
    ChildIndex
    -0.56
    RTLD
    -0.54
    UIControlState
    -0.53
    Zeneca
    -0.53
    SaveVideo
    -0.52
    __(/*!
    -0.50
    getWriter
    -0.50
    存于互联网档案馆
    -0.50
    nextInt
    -0.50
    POSITIVE LOGITS
     uska
    0.47
    rungsseite
    0.45
    atorul
    0.39
    ########.
    0.38
    TagMode
    0.35
    ITABLE
    0.35
     rozwo
    0.35
    DIPSETTING
    0.33
     lecz
    0.32
     sementara
    0.31
    Activations Density 0.078%

    No Known Activations