© 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
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 15432
    Prev
    Next
    INDEX
    Explanations

    specific formatting and syntax elements in programming code, particularly related to formatted output

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TestBed
    -0.42
     للاسماء
    -0.39
     chay
    -0.38
     lluvia
    -0.37
    StartTag
    -0.36
     détru
    -0.36
     privées
    -0.35
     joué
    -0.35
    PCell
    -0.35
    лтамалар
    -0.34
    POSITIVE LOGITS
    iomanip
    0.57
    DecimalFormat
    0.56
     format
    0.51
    format
    0.49
    breviated
    0.48
    huahua
    0.48
     accuracy
    0.47
    formatting
    0.46
     precision
    0.45
    chieht
    0.45
    Activations Density 0.257%

    No Known Activations