© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14217
    Prev
    Next
    INDEX
    Explanations

    references to system control features or limitations within technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    descriptions of personal experiences where someone is sharing their situation or story.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     harian
    -0.38
     entrevist
    -0.37
     actuelle
    -0.37
    ❷
    -0.37
     demás
    -0.37
     elsewhere
    -0.36
     entrevista
    -0.36
     diaria
    -0.34
     Barrios
    -0.34
    írito
    -0.34
    POSITIVE LOGITS
    Билгалдахарш
    0.51
     ddelweddau
    0.50
     InputDecoration
    0.47
     TextAppearance
    0.46
    quelize
    0.46
     дописавши
    0.45
    </>
    0.44
     ſtand
    0.42
    ACHUSET
    0.42
     foli
    0.42
    Activations Density 0.442%

    No Known Activations