© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6670
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to scientific measurements and scores

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

    that start with "S" followed by lowercase letters

    np_acts-logits-general · gemini-2.0-flash

    s/ca formulas

    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
    Халык
    -0.46
     alluminio
    -0.45
    𝕜
    -0.43
    argout
    -0.42
    BackColor
    -0.40
    getInt
    -0.40
    Toole
    -0.40
    𝕫
    -0.39
    jsonPath
    -0.39
    dymyr
    -0.39
    POSITIVE LOGITS
    SBATCH
    0.88
    sibirsk
    0.65
    SequentialGroup
    0.65
     SBS
    0.63
     sessionFactory
    0.61
    SBS
    0.60
     ſy
    0.60
    SceneManagement
    0.59
     ſon
    0.58
     gynhyrchwyd
    0.57
    Activations Density 2.218%

    No Known Activations