Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 1990
    Prev
    Next
    INDEX
    Explanations

    bits of code related to instructions and branching in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    بوابة
    -0.46
     majeur
    -0.46
    DJANGO
    -0.45
    tuj
    -0.43
    ÊN
    -0.43
    eben
    -0.42
    riges
    -0.42
     tutto
    -0.41
    Slap
    -0.41
     jegy
    -0.41
    POSITIVE LOGITS
    Hochspringen
    0.68
    endaft
    0.64
    wußt
    0.60
    NavController
    0.60
    boutin
    0.59
    BagLayout
    0.59
    WithIOException
    0.57
    SceneManagement
    0.56
    DockStyle
    0.55
    RenderAtEndOf
    0.55
    Activations Density 1.299%

    No Known Activations