© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 91242
    Prev
    Next
    INDEX
    Explanations

    code-related terms and structures, particularly pertaining to mutations and function definitions

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

    mutation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.52
     disambiguazione
    -0.51
    hilangan
    -0.45
    yordu
    -0.44
     Bioaccumulative
    -0.42
     Taschen
    -0.41
    hidupan
    -0.39
    ViewFeatures
    -0.37
    曖昧さ回避
    -0.37
     testGet
    -0.36
    POSITIVE LOGITS
     mutation
    0.93
     Mutation
    0.89
    Mutation
    0.87
     mutations
    0.83
     mut
    0.79
    mutation
    0.75
     Mut
    0.74
     Mutations
    0.73
    mutations
    0.73
    MUT
    0.73
    Activations Density 0.006%

    No Known Activations