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. 20-GEMMASCOPE-RES-16K
    6. 5150
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to community identities and social dynamics

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

    preceding suffixes: -ists, -ers, -kes, -ate, -ans, -ors, -citizen, -of, -B

    np_acts-logits-general · gemini-2.0-flash

    groups, nationalities, or roles

    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
    তথ্যসূত্র
    -0.62
    SequentialGroup
    -0.60
    TypedDataSet
    -0.59
    CppCodeGen
    -0.59
    Istorija
    -0.59
    DeleteBehavior
    -0.57
    writeField
    -0.53
    expandindo
    -0.53
     BoxDecoration
    -0.52
    неопр
    -0.51
    POSITIVE LOGITS
    standers
    0.84
    们
    0.80
     quienes
    0.71
    們
    0.68
     who
    0.66
    ients
    0.54
     takers
    0.53
    agers
    0.53
    iconque
    0.53
    ataires
    0.52
    Activations Density 0.479%

    No Known Activations