© 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. 28-GEMMASCOPE-RES-16K
    11. 8369
    Prev
    Next
    INDEX
    Explanations

    numerical values and dates

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

    Numbers followed by date information

    np_acts-logits-general · gemini-2.0-flash

    dates and months

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.33
     intégr
    -0.30
    Has
    -0.29
     element
    -0.29
    bardziej
    -0.28
    amuk
    -0.28
     Has
    -0.28
     tích
    -0.28
     who
    -0.27
     whose
    -0.27
    POSITIVE LOGITS
     nahilalakip
    0.89
    InjectAttribute
    0.75
    aarrggbb
    0.71
    protoimpl
    0.70
    UrlResolution
    0.69
     initComponents
    0.69
    parsedMessage
    0.67
    IntoConstraints
    0.66
    存于互联网档案馆
    0.66
    WithIOException
    0.65
    Activations Density 0.395%

    No Known Activations