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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15436
    Prev
    Next
    INDEX
    Explanations

    programming-related code constructs and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     ब्रेकडाउन
    -0.95
    AddTagHelper
    -0.90
    Vidite
    -0.83
    Personensuche
    -0.82
    ValueStyle
    -0.81
    tagHelperRunner
    -0.81
    évaluateur
    -0.81
    <unused68>
    -0.81
    [@BOS@]
    -0.80
    <unused8>
    -0.80
    POSITIVE LOGITS
     Tiefen
    0.33
     Königin
    0.29
    ↵↵
    0.29
     Schulte
    0.29
     aislado
    0.29
     perto
    0.28
     manuales
    0.28
     Gobernador
    0.28
     corriendo
    0.27
    flashdata
    0.27
    Activations Density 0.523%

    No Known Activations