© 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. 19-GEMMASCOPE-RES-16K
    11. 2351
    Prev
    Next
    INDEX
    Explanations

    references to locations or descriptions of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.62
    PutMapping
    -0.49
    bacher
    -0.46
    如
    -0.45
    にな
    -0.45
    poň
    -0.43
    lieu
    -0.43
    JAKARTA
    -0.43
    .
    -0.43
    jeeling
    -0.42
    POSITIVE LOGITS
     myſelf
    1.16
     itſelf
    0.99
     Monfieur
    0.97
     whoſe
    0.94
     raiſ
    0.94
     uſed
    0.93
     themſelves
    0.93
     poffe
    0.90
     himſelf
    0.89
     ſy
    0.89
    Activations Density 0.749%

    No Known Activations