© 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. 4-GEMMASCOPE-RES-16K
    11. 9870
    Prev
    Next
    INDEX
    Explanations

    references to relationships and connections among various elements and entities within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.58
    ाषा
    -0.50
     getchar
    -0.47
    chließend
    -0.47
     gepubliceerd
    -0.46
    #+#
    -0.46
    ėk
    -0.45
    ̣n
    -0.45
    nasel
    -0.45
     getM
    -0.44
    POSITIVE LOGITS
     Meksiku
    0.80
     indisponible
    0.73
    prefixer
    0.71
    aarrggbb
    0.70
     Signalez
    0.68
    RenderAtEndOf
    0.68
     consultato
    0.68
    Clik
    0.63
     CommonModule
    0.62
    RefNanny
    0.59
    Activations Density 1.045%

    No Known Activations