© 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. 9-GEMMASCOPE-RES-131K
    6. 55522
    Prev
    Next
    INDEX
    Explanations

    variations of quotation marks or apostrophes

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

    possessive 's

    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
    fjspx
    -0.57
     AssemblyCulture
    -0.50
    AutoScaleMode
    -0.50
     typelib
    -0.46
    WithIOException
    -0.45
    RoutingModule
    -0.43
    ValueStyle
    -0.42
    GHIJKLM
    -0.42
    Externé
    -0.40
     NSCoder
    -0.40
    POSITIVE LOGITS
    INCREF
    0.50
    :“……”
    0.47
    猛地
    0.47
     gezet
    0.44
     poveznice
    0.43
    mobileqq
    0.43
    Quickly
    0.43
     alarmed
    0.43
    Filmografia
    0.42
     Identities
    0.42
    Activations Density 0.079%

    No Known Activations