© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1407
    Prev
    Next
    INDEX
    Explanations

    conjunctions and references to personal experiences

    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
     kuli
    -0.45
    ضي
    -0.43
     intrusions
    -0.43
     Hacking
    -0.42
     plaat
    -0.42
    stow
    -0.42
     било
    -0.42
     fibrillation
    -0.42
    ueur
    -0.41
     Gere
    -0.41
    POSITIVE LOGITS
     كومونز
    0.92
    WriteBarrier
    0.83
    offsetof
    0.77
    InjectAttribute
    0.75
    AsUp
    0.74
    RTLD
    0.73
     للمعارف
    0.72
     >=",
    0.72
    SequentialGroup
    0.72
    ORCID
    0.72
    Activations Density 0.206%

    No Known Activations