© 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. 733
    Prev
    Next
    INDEX
    Explanations

    terms related to engineering and technical specifications

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

    before ", and" or ", generic"

    np_acts-logits-general · gemini-2.0-flash

    machines and electronics

    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
    webElement
    -0.47
     AspNetCore
    -0.45
    toHaveBeenCalled
    -0.42
    GenerationType
    -0.41
    CodedInputStream
    -0.39
    ngrx
    -0.39
    djangoproject
    -0.39
    redacted
    -0.36
     deserved
    -0.36
    patched
    -0.36
    POSITIVE LOGITS
    ivoli
    0.45
     autorytatywna
    0.45
     Tiz
    0.43
    httphttps
    0.43
     Spice
    0.43
     studies
    0.43
    Spice
    0.42
     scientists
    0.42
    nloa
    0.42
     Studies
    0.42
    Activations Density 0.529%

    No Known Activations