© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10044
    Prev
    Next
    INDEX
    Explanations

    essential recommendations or things deemed necessary in various contexts

    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
    ViewFeatures
    -0.54
    ẽ
    -0.49
    PyExc
    -0.47
    ymce
    -0.47
     numerus
    -0.47
    )="
    -0.46
    twimg
    -0.44
     sti
    -0.43
    posted
    -0.41
    bois
    -0.41
    POSITIVE LOGITS
     favorites
    1.10
     classics
    1.08
     favourites
    1.06
     favourite
    1.02
     favorite
    1.02
     estekak
    0.96
     classic
    0.95
     classiques
    0.94
     Favourite
    0.91
    favourite
    0.90
    Activations Density 0.389%

    No Known Activations