© 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. 18117
    Prev
    Next
    INDEX
    Explanations

    terms related to companies and products that are discontinued or deprecated

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

    defunct, deprecated, or obsolete items

    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
    RTSC
    -0.32
    发表于
    -0.31
    ロード
    -0.31
    RuleContext
    -0.29
     das
    -0.29
    Rè
    -0.28
    plish
    -0.28
     bil
    -0.28
     Kami
    -0.28
     exhibit
    -0.27
    POSITIVE LOGITS
    ftagPool
    0.73
    jetunion
    0.60
     Deprecated
    0.60
     Taktlose
    0.60
    ̈́
    0.55
    GONE
    0.54
    rones
    0.54
    ioneers
    0.54
    bootstrapcdn
    0.54
     obsolete
    0.54
    Activations Density 0.168%

    No Known Activations