© 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. 1858
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and research findings

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

    academic or scientific references and citations.

    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
     OMITBAD
    -0.71
    endphp
    -0.66
    GEBURTS
    -0.59
     purpoſe
    -0.55
     pinulongan
    -0.54
    fromnode
    -0.54
    parsedMessage
    -0.54
     nahilalakip
    -0.54
     unknownFields
    -0.53
    ésultats
    -0.53
    POSITIVE LOGITS
     another
    0.81
     similarly
    0.69
    another
    0.69
    Another
    0.67
     also
    0.64
     Another
    0.63
     similar
    0.61
     ANOTHER
    0.53
    also
    0.52
     ebenfalls
    0.51
    Activations Density 0.454%

    No Known Activations