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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 715
    Prev
    Next
    INDEX
    Explanations

    specific nouns related to categories, entities, or roles

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

    specific numerical quantities or counts.

    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
     Comunicação
    -0.47
     Gestão
    -0.46
     prefeitura
    -0.45
     počet
    -0.43
     pinulongan
    -0.42
     ویکی‌پدیای
    -0.42
     apunta
    -0.41
     Trabalho
    -0.41
     apunt
    -0.40
     Justiça
    -0.39
    POSITIVE LOGITS
     समीक्षक
    0.56
     SRL
    0.48
    ASR
    0.47
    ittarius
    0.47
     ALC
    0.46
     ASF
    0.46
     NOL
    0.45
    ="@+
    0.44
    ASF
    0.44
     BOP
    0.44
    Activations Density 0.522%

    No Known Activations