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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 11819
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of places and institutions

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

    German cities and universities

    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
     esternos
    -0.38
     ModelRenderer
    -0.37
    Pranala
    -0.34
     Englisch
    -0.31
    jetbrains
    -0.30
     roul
    -0.30
     COMPLEX
    -0.30
     som
    -0.29
    cline
    -0.29
    リーナ
    -0.28
    POSITIVE LOGITS
    PostInfinity
    0.66
     Drapeau
    0.63
    IntoConstraints
    0.60
     queſta
    0.57
     beginnetje
    0.56
    LabelTagHelper
    0.54
    原始内容存档于
    0.51
    ロウィン
    0.51
    OGND
    0.50
    NameInMap
    0.48
    Activations Density 0.062%

    No Known Activations