© 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. 21-GEMMASCOPE-RES-16K
    6. 8649
    Prev
    Next
    INDEX
    Explanations

    content related to documentation, reporting, or records, particularly in an administrative or bureaucratic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -1.46
    withstanding
    -1.40
    foundland
    -1.15
    dawnictwo
    -1.14
    tonsoft
    -1.13
    giveness
    -1.03
    нрави
    -1.02
    tably
    -1.00
    imantan
    -0.98
    oubtedly
    -0.97
    POSITIVE LOGITS
    guien
    0.84
    stood
    0.74
    ButtonModule
    0.68
    IconModule
    0.63
    ocidad
    0.59
    dasarkan
    0.59
    здрав
    0.56
    достатки
    0.54
    ulario
    0.54
    uiente
    0.53
    Activations Density 0.836%

    No Known Activations