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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6520
    Prev
    Next
    INDEX
    Explanations

    key characters and their roles within a narrative, particularly focusing on villains and their motivations

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

    Space war, rebellion, or invasion stories

    np_acts-logits-general · gemini-2.0-flash

    space invasion and conquest

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    GeneratedCode
    -0.38
     męska
    -0.38
     feroit
    -0.35
     baumwolle
    -0.34
     Latein
    -0.34
     mę
    -0.33
     auroit
    -0.32
     préféré
    -0.31
    illermo
    -0.31
     essentiel
    -0.31
    POSITIVE LOGITS
    TagMode
    0.66
    setVerticalGroup
    0.62
    AnchorStyles
    0.60
    DockStyle
    0.60
    :✨
    0.54
    MigrationBuilder
    0.54
    InputBorder
    0.54
     surla
    0.54
    yntaxException
    0.54
    TypedDataSet
    0.53
    Activations Density 0.686%

    No Known Activations