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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8347
    Prev
    Next
    INDEX
    Explanations

    elements of narrative structure and character interactions within a story

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

    Tokens preceding furniture-related words

    np_acts-logits-general · gemini-2.0-flash

    tables and desks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    Handlung
    -0.60
    KommentareTeilen
    -0.59
    HandlerContext
    -0.57
    Solución
    -0.56
     paille
    -0.56
    πει
    -0.53
    ItemLayout
    -0.50
    BuilderFactory
    -0.50
    ersonic
    -0.50
     HttpNotFound
    -0.49
    POSITIVE LOGITS
     table
    1.52
     tables
    1.27
     desk
    1.09
     Table
    1.02
    table
    1.02
     meja
    0.99
     tabletop
    0.98
     counter
    0.96
     Tables
    0.94
     desks
    0.93
    Activations Density 0.148%

    No Known Activations