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. 32-GEMMASCOPE-RES-131K
    6. 130050
    Prev
    Next
    INDEX
    Explanations

    technical commands and terms related to user permissions and authentication in a system

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

    user id or group index

    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_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnsafeEnabled
    -0.49
    __))
    -0.47
    >>()
    -0.47
    farol
    -0.43
     Exactos
    -0.43
    nthetic
    -0.42
    __);
    -0.42
    VELAND
    -0.41
    AndEndTag
    -0.41
     alve
    -0.41
    POSITIVE LOGITS
     Италијани
    0.58
     grupo
    0.52
    NgModule
    0.51
     grupa
    0.48
     group
    0.48
     uid
    0.47
     grupos
    0.47
    GID
    0.46
     groups
    0.45
    UID
    0.45
    Activations Density 0.060%

    No Known Activations