© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 85103
    Prev
    Next
    INDEX
    Explanations

    instances of "dotted" lines or patterns throughout the text

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

    dotted lines and visual marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Superhost
    -0.47
    ConstraintMaker
    -0.47
    AccessControl
    -0.45
     incontr
    -0.44
     prisonniers
    -0.44
     język
    -0.43
     réus
    -0.43
     Komunikasi
    -0.42
     navidad
    -0.42
     kapture
    -0.42
    POSITIVE LOGITS
     dotted
    1.82
    dotted
    1.55
     dashed
    1.05
    dashed
    1.02
     studded
    0.94
    studded
    0.82
     speckled
    0.71
     spotted
    0.71
     padded
    0.65
     Spotted
    0.63
    Activations Density 0.010%

    No Known Activations