© 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. 10585
    Prev
    Next
    INDEX
    Explanations

    elements of structured programming and syntactical markers in code

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

    Mathematical or code-related symbols

    np_acts-logits-general · gemini-2.0-flash

    code or mathematical notation

    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
     الرياضيه
    -0.88
     surla
    -0.70
     ब्रेकडाउन
    -0.65
    лтамалар
    -0.64
     nahilalakip
    -0.63
    rungsseite
    -0.63
    protoimpl
    -0.59
    ########.
    -0.59
    AISSEE
    -0.58
    WaitGroup
    -0.57
    POSITIVE LOGITS
    ان
    0.39
    les
    0.36
    cian
    0.35
    Toolbar
    0.35
     Med
    0.35
    Bar
    0.34
    cuda
    0.33
    acia
    0.33
    ddd
    0.32
    Med
    0.31
    Activations Density 0.621%

    No Known Activations