© 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. 4264
    Prev
    Next
    INDEX
    Explanations

    sentences containing technical or biblical references along with data standards and measurements

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

    Codes (e.g. ASTM, Fed.R.Evid., GO) followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and codes

    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
    OCCURRED
    -0.46
     <<<<<<<<<<<<<<
    -0.40
    AccessorTable
    -0.31
    SharedCtor
    -0.27
    Décès
    -0.27
     submitted
    -0.27
     łat
    -0.26
    ineno
    -0.25
     meny
    -0.25
    MergeFrom
    -0.25
    POSITIVE LOGITS
    parsedMessage
    0.64
    rawDesc
    0.60
    ChildScrollView
    0.60
     MessageBoxIcon
    0.60
    Portale
    0.60
    Dichlor
    0.58
     ब्रेकडाउन
    0.53
    点此举报
    0.52
    Rptr
    0.52
    ItemBackground
    0.52
    Activations Density 0.768%

    No Known Activations