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. 19-GEMMASCOPE-RES-16K
    6. 11262
    Prev
    Next
    INDEX
    Explanations

    instances of moments of realization or significant insights in life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.63
    srcs
    -0.54
    KommentareTeilen
    -0.54
    })$}
    -0.54
     linkovi
    -0.53
    Conclusie
    -0.52
    Nachteile
    -0.50
    tvguidetime
    -0.49
    rededor
    -0.48
    lungen
    -0.48
    POSITIVE LOGITS
     moment
    2.81
     moments
    2.68
    moment
    2.54
     Moment
    2.38
    Moment
    2.35
    moments
    2.32
     Moments
    2.23
     MOMENT
    2.10
    Moments
    2.08
     momento
    1.94
    Activations Density 0.207%

    No Known Activations