© 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. 25-GEMMASCOPE-RES-16K
    11. 5101
    Prev
    Next
    INDEX
    Explanations

    header or section markers related to programming or code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    órios
    -0.53
    +/**
    -0.53
     الرياضيه
    -0.52
    kháu
    -0.50
    KELEY
    -0.48
    kań
    -0.46
    BASELINE
    -0.46
    (
    -0.46
    ünste
    -0.45
    tapi
    -0.45
    POSITIVE LOGITS
    ️⃣
    1.16
    ⃣
    0.99
     noqa
    0.95
    SPJ
    0.86
    include
    0.83
    pragma
    0.79
    define
    0.79
    !/
    0.76
    shorts
    0.74
    Repost
    0.70
    Activations Density 0.278%

    No Known Activations