© 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. 38411
    Prev
    Next
    INDEX
    Explanations

    references to dogs and their tracking abilities

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

    sniffing dog

    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
    downloaded
    -0.38
     cromado
    -0.37
    ONSORED
    -0.37
     guerres
    -0.36
    ddots
    -0.36
     reflejo
    -0.35
    jsoup
    -0.35
     chapéu
    -0.35
    CopyWith
    -0.35
     surla
    -0.35
    POSITIVE LOGITS
    SequentialGroup
    0.60
    EndContext
    0.52
    脚注の使い方
    0.49
     rescue
    0.49
     airborne
    0.48
    adaptiveStyles
    0.47
     AttributeError
    0.46
    لينكات
    0.45
     Airborne
    0.44
    ########.
    0.44
    Activations Density 0.152%

    No Known Activations