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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12348
    Prev
    Next
    INDEX
    Explanations

    elements related to programming code structure and definitions

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

    Code, assembly, or configuration files

    np_acts-logits-general · gemini-2.0-flash

    starts of inputs or code blocks

    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
     منهم
    -0.41
    XtraBars
    -0.39
    BeginContext
    -0.36
    TypedDataSet
    -0.30
     منها
    -0.30
     instante
    -0.30
    argout
    -0.30
     culte
    -0.29
    InjectMocks
    -0.29
    menubar
    -0.29
    POSITIVE LOGITS
    :+:
    0.59
    Autoritní
    0.57
    RuleContext
    0.56
    허
    0.55
    ########.
    0.54
    tagHelperRunner
    0.54
     '\\;'
    0.53
    OCCURRED
    0.52
    Filmografie
    0.50
    ]--;
    0.50
    Activations Density 0.958%

    No Known Activations