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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4467
    Prev
    Next
    INDEX
    Explanations

    references to specific classes or categories in various contexts

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

    The token "class"

    np_acts-logits-general · gemini-2.0-flash

    class

    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
    AndEndTag
    -0.65
     aceptas
    -0.60
    webElementXpaths
    -0.55
    familien
    -0.55
    🏿
    -0.54
    ubernur
    -0.53
    Phases
    -0.51
    🏽
    -0.50
    लग
    -0.50
     légales
    -0.50
    POSITIVE LOGITS
    rooms
    0.89
    ically
    0.89
    ROOM
    0.76
    CastException
    0.72
    sieke
    0.71
    mates
    0.67
    ics
    0.63
    ROOMS
    0.62
    fication
    0.60
    mate
    0.60
    Activations Density 0.111%

    No Known Activations