© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6763
    Prev
    Next
    INDEX
    Explanations

    references to programming languages and technical terminology

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

    Code syntax errors or parsing

    np_acts-logits-general · gemini-2.0-flash

    AST syntax tokens and nodes

    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
    rrggbb
    -0.77
    AddTagHelper
    -0.71
     queſta
    -0.71
    OGND
    -0.69
    ſcher
    -0.67
    ſchen
    -0.67
     يتيمه
    -0.67
    RTLI
    -0.66
    tagHelperRunner
    -0.66
     newOwner
    -0.66
    POSITIVE LOGITS
     licencia
    0.32
     secuencia
    0.31
     Brücke
    0.31
     herramienta
    0.29
     fases
    0.29
     máscaras
    0.29
     maquinaria
    0.29
     sepol
    0.29
     gutem
    0.29
     procès
    0.28
    Activations Density 0.387%

    No Known Activations