© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 15762
    Prev
    Next
    INDEX
    Explanations

    terms related to research methodology and data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    -0.77
     lenker
    -0.71
    Tikang
    -0.69
    providedIn
    -0.69
    Personensuche
    -0.66
     OFDb
    -0.63
    קישורים
    -0.62
    навли
    -0.60
     متعلقه
    -0.58
     transfieras
    -0.58
    POSITIVE LOGITS
    ثيق
    0.68
     text
    0.58
    StandardCharsets
    0.56
     format
    0.56
    erte
    0.54
    iotti
    0.53
    izo
    0.53
     presentations
    0.52
    dui
    0.51
     gebra
    0.51
    Activations Density 2.917%

    No Known Activations