© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5438
    Prev
    Next
    INDEX
    Explanations

    significant mentions of entities and key numerical data in contexts related to research and analysis

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

    technical or scientific terminology, particularly related to research methods and experimental details.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    ,
    -0.52
    .
    -0.32
     (
    -0.31
     "
    -0.30
     of
    -0.28
     in
    -0.28
     on
    -0.27
     International
    -0.26
    "
    -0.26
    …
    -0.25
    POSITIVE LOGITS
    +#+#
    1.04
    rungsseite
    0.93
    iſchen
    0.90
    ſſung
    0.90
    <unused43>
    0.89
    niſſe
    0.89
    <unused41>
    0.88
    <pad>
    0.88
    <unused76>
    0.88
    <unused79>
    0.88
    Activations Density 0.455%

    No Known Activations