© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2154
    Prev
    Next
    INDEX
    Explanations

    connections and relationships in reasoning and arguments

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

    that indicate possibility or uncertainty

    np_acts-logits-general · gemini-2.0-flash

    foreign language words

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    PerformLayout
    -0.59
     propOrder
    -0.59
     wireType
    -0.54
    MessageOf
    -0.52
     transfieras
    -0.52
    dibles
    -0.51
     Autorisations
    -0.51
    endphp
    -0.51
     polig
    -0.51
    toHaveBeenCalled
    -0.50
    POSITIVE LOGITS
    fjspx
    0.33
     cadeiras
    0.32
    Presenta
    0.31
     amitié
    0.31
     resourceCulture
    0.31
     lisäksi
    0.31
     inoltre
    0.30
     asociados
    0.30
     szkole
    0.30
     flechas
    0.30
    Activations Density 0.752%

    No Known Activations