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. 3-GEMMASCOPE-RES-16K
    6. 1039
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to biomedical research and genetic analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -1.18
    :✨
    -1.11
    +#+#
    -1.11
     nahilalakip
    -1.09
     resourceCulture
    -0.96
    XmlEnum
    -0.93
    UnusedPrivate
    -0.93
    featureID
    -0.86
     Paglinawan
    -0.84
     <=",
    -0.84
    POSITIVE LOGITS
     vectorielle
    0.54
     vastaan
    0.51
     secco
    0.49
     acrylique
    0.46
     skjø
    0.46
     optique
    0.46
    enoord
    0.45
     intellectuelle
    0.45
     esist
    0.45
    фициальный
    0.44
    Activations Density 3.900%

    No Known Activations