© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 67014
    Prev
    Next
    INDEX
    Explanations

    mathematical structures and properties related to rings and vector spaces

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

    vector space structure and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.75
    styleType
    -0.71
    RTGC
    -0.68
    GEBURTS
    -0.68
    IntoConstraints
    -0.64
     ſei
    -0.64
     queſta
    -0.64
    LLocation
    -0.63
    OGND
    -0.60
     beſte
    -0.60
    POSITIVE LOGITS
     dispozici
    0.32
     ruedas
    0.31
     Einleitung
    0.31
     handeln
    0.30
    function
    0.30
     indústria
    0.30
     treat
    0.30
     olet
    0.29
     plus
    0.29
     Ejecutivo
    0.29
    Activations Density 0.172%

    No Known Activations