© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 127717
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols, particularly related to equations or formulas

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

    LaTeX delimiters

    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
     propOrder
    -0.53
     rękaw
    -0.46
     preghiera
    -0.46
     EventEmitter
    -0.45
     vacanza
    -0.45
    OwnProperty
    -0.44
     goederen
    -0.44
     recensione
    -0.44
    guisement
    -0.43
    eventId
    -0.42
    POSITIVE LOGITS
    *}
    2.28
    *}\
    1.20
    *}
    
    1.05
    *}$
    1.03
    *]
    0.83
     *}
    0.77
     }^{*}
    0.72
    *}[
    0.70
    |}
    0.68
    +}
    0.63
    Activations Density 0.007%

    No Known Activations