© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122467
    Prev
    Next
    INDEX
    Explanations

    actions related to planning, assessing, and improving organizational processes

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

    identify, investigate, analyze, study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     dAtA
    -0.35
     âmes
    -0.34
    ênero
    -0.32
     Gar
    -0.32
    AFFIRMED
    -0.31
    INTENANCE
    -0.31
     Schar
    -0.31
    搭
    -0.31
    upsi
    -0.31
    jenje
    -0.31
    POSITIVE LOGITS
    @[+][
    0.58
    EDEFAULT
    0.57
     législation
    0.56
    ioutil
    0.52
    ьажоргаш
    0.49
     jsPsych
    0.48
     glaciers
    0.47
     cherchés
    0.47
    makeText
    0.47
     <>",
    0.47
    Activations Density 0.020%

    No Known Activations