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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19689
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific notation, particularly related to vector or matrix operations

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

    probability $P(ABC)$

    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
    AnimationsModule
    -0.46
    VersionUID
    -0.46
     Molina
    -0.42
     Méndez
    -0.39
     Botschaft
    -0.38
     Sarmiento
    -0.37
     Pacheco
    -0.37
     Ramírez
    -0.36
    NgModule
    -0.36
     defaultstate
    -0.36
    POSITIVE LOGITS
     ModelExpression
    0.51
     للاسماء
    0.47
    tagHelperRunner
    0.47
    IsMutable
    0.46
    InitVars
    0.45
    Diweddarwch
    0.45
     Chwiliwch
    0.44
    SequentialGroup
    0.42
    Nuorodos
    0.41
     Мексичка
    0.40
    Activations Density 0.069%

    No Known Activations