© 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. 534
    Prev
    Next
    INDEX
    Explanations

    processes and steps involved in methodologies or instructions

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

    progression or gradual change

    np_acts-logits-general · gemini-2.0-flash

    gradual successive steps

    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
     Taktlose
    -0.56
    stdc
    -0.55
     الحره
    -0.53
     referrerpolicy
    -0.52
    hyrchwyd
    -0.52
     lenker
    -0.50
    ioutil
    -0.50
    RuleContext
    -0.48
    saraba
    -0.47
    migrationBuilder
    -0.46
    POSITIVE LOGITS
     successive
    0.71
     progressive
    0.71
     sequentially
    0.70
     progressively
    0.69
     stages
    0.69
     progres
    0.69
     progression
    0.68
     steps
    0.68
     gradually
    0.67
     gradual
    0.66
    Activations Density 0.918%

    No Known Activations