© 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. 6618
    Prev
    Next
    INDEX
    Explanations

    structured data and references within technical or coding contexts

    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
    fören
    -0.68
    verhält
    -0.62
    stufen
    -0.60
    genossen
    -0.59
    losigkeit
    -0.59
     Перейти
    -0.58
    würdig
    -0.57
    vermögen
    -0.57
    stufe
    -0.56
    ständen
    -0.56
    POSITIVE LOGITS
    -
    3.33
    ‑
    1.52
    ‐
    1.38
    -​
    1.29
    ®-
    1.25
    -...
    1.23
    -<
    1.20
    -'
    1.15
    -
    1.12
    -$
    1.09
    Activations Density 6.069%

    No Known Activations