© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 10828
    Prev
    Next
    INDEX
    Explanations

    mentions of lines and their associated formatting or characteristics in a document

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

    "line" or "Lines"

    np_acts-logits-general · gemini-2.0-flash

    line or lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    掴
    -0.41
     Carnaval
    -0.40
    carpus
    -0.40
    ~*~
    -0.40
     Scha
    -0.40
     youngest
    -0.40
    superuser
    -0.40
    tacular
    -0.39
     smallest
    -0.39
    #!/
    -0.39
    POSITIVE LOGITS
    Line
    1.32
     Line
    1.30
     line
    1.23
     LINE
    1.22
    line
    1.18
    LINE
    1.14
    Lines
    1.03
     Lines
    1.02
    lines
    1.01
     LINES
    0.96
    Activations Density 0.157%

    No Known Activations