© 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. 25-GEMMASCOPE-RES-16K
    11. 1169
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    которые
    -1.33
    withstanding
    -1.12
    tonsoft
    -0.92
    foundland
    -0.91
    giveness
    -0.89
    нрави
    -0.86
    etheless
    -0.84
    oubtedly
    -0.84
    dawnictwo
    -0.81
    tably
    -0.81
    POSITIVE LOGITS
    ButtonModule
    0.61
    IconModule
    0.60
    stood
    0.58
     ويكيميديا
    0.58
    guien
    0.54
    notations
    0.52
    InputModule
    0.50
    uiente
    0.50
    PRNewswire
    0.48
    miary
    0.48
    Activations Density 0.651%

    No Known Activations