© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 16253
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     capucha
    -0.28
    ạp
    -0.28
    tagext
    -0.26
    Signal
    -0.25
     Signal
    -0.24
     accompagne
    -0.24
     Schulter
    -0.23
    无所
    -0.23
     aislado
    -0.23
    olahan
    -0.23
    POSITIVE LOGITS
    esModule
    0.91
    adeloupe
    0.78
    rungsseite
    0.77
    arangay
    0.73
    atemala
    0.69
    ſſung
    0.68
    Autoritní
    0.66
     laſſen
    0.65
     beſte
    0.65
    ſelf
    0.64
    Activations Density 0.231%

    No Known Activations