© 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. 66060
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting related to mathematical or logical representations

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

    mathematical symbols and formulas

    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
     profilo
    -0.32
    <sup>
    -0.31
    <sub>
    -0.30
    いくつか
    -0.30
     następu
    -0.29
     Pia
    -0.29
    -
    -0.29
     nostro
    -0.28
    Marianne
    -0.28
    oro
    -0.28
    POSITIVE LOGITS
    awtextra
    0.85
    mtd
    0.73
    Personendaten
    0.72
    MLLoader
    0.65
     ExecuteAsync
    0.63
     propOrder
    0.63
     gră
    0.62
    stateProvider
    0.61
    RTLR
    0.60
    JspWriter
    0.60
    Activations Density 0.030%

    No Known Activations