Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8478
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "even."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataAnnotations
    -0.49
     Audiodateien
    -0.48
     HasFactory
    -0.48
    efforts
    -0.45
     penghargaan
    -0.45
    unnitel
    -0.44
    ratory
    -0.42
     elä
    -0.42
     pihaknya
    -0.42
    RenderAtEndOf
    -0.42
    POSITIVE LOGITS
     pattern
    0.70
    pattern
    0.61
     PATTERN
    0.59
     Pattern
    0.57
     ब्रेकडाउन
    0.54
    Pattern
    0.54
     patterns
    0.54
     Patterns
    0.51
    patterns
    0.50
     Swit
    0.48
    Activations Density 0.106%

    No Known Activations