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. 20-GEMMASCOPE-RES-16K
    6. 12772
    Prev
    Next
    INDEX
    Explanations

    elements of suspense and dramatic tension in narrative descriptions

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

    followed by time-related words

    np_acts-logits-general · gemini-2.0-flash

    describing moments

    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
    KommentareTeilen
    -0.58
     AssemblyTitle
    -0.55
    PyExc
    -0.55
    rededor
    -0.54
    Conclusie
    -0.54
    }{*}{}
    -0.53
     extensão
    -0.53
    }^{+\
    -0.51
    internalType
    -0.51
    tvguidetime
    -0.50
    POSITIVE LOGITS
     moments
    2.39
     moment
    2.31
    moment
    2.04
    moments
    2.01
     Moments
    1.92
     Moment
    1.90
    Moment
    1.88
    Moments
    1.79
     MOMENT
    1.69
     momenti
    1.61
    Activations Density 0.238%

    No Known Activations