© 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. 7-GEMMASCOPE-RES-16K
    6. 7299
    Prev
    Next
    INDEX
    Explanations

    mathematical constructs and notation related to arrays or matrices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jenje
    -0.51
    OGND
    -0.45
     capuche
    -0.44
    зо
    -0.42
    ougou
    -0.41
     Shiloh
    -0.39
    益
    -0.39
     ilustracja
    -0.39
     klart
    -0.39
    acije
    -0.39
    POSITIVE LOGITS
    StoryboardSegue
    0.95
     resourceCulture
    0.86
    substack
    0.86
    IntoConstraints
    0.83
    interopRequire
    0.79
    providedIn
    0.78
     noqa
    0.77
    ArgumentParser
    0.77
     AssemblyCulture
    0.77
     Савезне
    0.76
    Activations Density 0.141%

    No Known Activations