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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 94245
    Prev
    Next
    INDEX
    Explanations

    references to paperwork and associated processes

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

    paperwork and documentation

    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
    inafter
    -0.39
    oplan
    -0.38
    unks
    -0.38
     spars
    -0.36
    verwijspagina
    -0.36
     INDUSTRIES
    -0.36
    chê
    -0.35
    ernen
    -0.35
     Psycho
    -0.35
    pezi
    -0.35
    POSITIVE LOGITS
     paperwork
    0.75
    Papers
    0.59
     papers
    0.57
     Autorizaciones
    0.56
     documents
    0.56
     papeles
    0.56
    Documents
    0.54
    yntaxException
    0.54
     documentation
    0.53
    documents
    0.52
    Activations Density 0.158%

    No Known Activations