© 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. 85257
    Prev
    Next
    INDEX
    Explanations

    terms related to optical interference and measurement setups

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

    optical paths and measurements

    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
    MessageOf
    -0.68
    الحياه
    -0.59
    prefixer
    -0.56
    XmlAccessType
    -0.56
    исленность
    -0.53
    GraphicsUnit
    -0.53
    IsMutable
    -0.52
    تفصیلات
    -0.50
    ItemBackground
    -0.50
     FetchType
    -0.49
    POSITIVE LOGITS
    posedge
    0.43
    #+#
    0.32
     classical
    0.32
    สู
    0.31
     obispo
    0.30
     streaming
    0.30
    INSEE
    0.30
     senador
    0.29
    TestId
    0.28
    ConfigureAwait
    0.28
    Activations Density 0.230%

    No Known Activations