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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4578
    Prev
    Next
    INDEX
    Explanations

    elements related to societal behaviors and individual contributions within various contexts

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

    Something being discarded or removed

    np_acts-logits-general · gemini-2.0-flash

    put aside or removed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.77
    WithIOException
    -0.77
    adpleegd
    -0.73
    UnusedPrivate
    -0.73
    !(:
    -0.71
    ValueStyle
    -0.69
    Jeografia
    -0.68
    jooq
    -0.68
    Vidite
    -0.67
    LabelTagHelper
    -0.66
    POSITIVE LOGITS
     aside
    0.97
    aside
    0.76
     sidelined
    0.68
     relegated
    0.68
     کنار
    0.63
     discarded
    0.60
     Aside
    0.59
     out
    0.56
     banished
    0.55
     sidelines
    0.53
    Activations Density 0.207%

    No Known Activations