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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15291
    Prev
    Next
    INDEX
    Explanations

    phrases that describe the effects of variables or conditions in scientific contexts

    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
    AccessFile
    -0.83
     allAfrica
    -0.67
    findpost
    -0.64
    ganu
    -0.63
    IBarButtonItem
    -0.58
     Audiodateien
    -0.55
    ंदीखरीदारी
    -0.55
     knex
    -0.54
    yntaxException
    -0.54
    jake
    -0.51
    POSITIVE LOGITS
     samping
    0.73
     fallu
    0.70
    клопе
    0.69
     spéciaux
    0.67
     Eff
    0.66
    帖最后由
    0.64
    IVENESS
    0.64
    tivitas
    0.61
     fédé
    0.60
     levier
    0.58
    Activations Density 0.132%

    No Known Activations