© 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. 8-GEMMASCOPE-RES-16K
    11. 4483
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical analysis and adjustments in research studies

    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
     ***!
    -0.49
     MainAxisSize
    -0.49
    bildet
    -0.49
     tantôt
    -0.49
     yerine
    -0.48
    UpInside
    -0.48
     melay
    -0.47
     stedet
    -0.47
     invece
    -0.47
    MoveNext
    -0.47
    POSITIVE LOGITS
    NameInMap
    0.63
    mybatisplus
    0.62
     Италијани
    0.61
     protoimpl
    0.59
    Adjusted
    0.59
    unconfirmed
    0.58
    addCriterion
    0.56
    afficheront
    0.56
    AntiForgeryToken
    0.56
    WithIOException
    0.56
    Activations Density 0.562%

    No Known Activations