© 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. 9-GEMMASCOPE-RES-131K
    11. 107390
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols related to sentence endings and pauses

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

    Eider, Andrew, Schleswig, assumption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.63
    valdi
    -0.51
    culin
    -0.50
    ooplankton
    -0.49
    choon
    -0.49
    olverine
    -0.47
    utiva
    -0.47
    puri
    -0.46
    OMEM
    -0.46
    fante
    -0.46
    POSITIVE LOGITS
     nahilalakip
    0.52
     typelib
    0.47
    cessite
    0.43
    canestro
    0.43
     iconLine
    0.42
    –¿
    0.41
    ResumeLayout
    0.40
    AsUp
    0.39
    hésite
    0.39
    évaluateur
    0.39
    Activations Density 0.002%

    No Known Activations