© 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. 4177
    Prev
    Next
    INDEX
    Explanations

    structured data and programming constructs related to system information and resource management

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

    low-level computer programming syntax and memory-related terminology.

    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
    URLException
    -0.57
    Autoritní
    -0.41
     flake
    -0.41
    ckså
    -0.40
     nonatomic
    -0.40
     démocratique
    -0.40
    ksikon
    -0.40
    ParseTree
    -0.40
    SourceChecksum
    -0.39
     ""));
    -0.39
    POSITIVE LOGITS
    findpost
    0.58
    soka
    0.43
    MessageOf
    0.41
     Listen
    0.41
    XmlAccessType
    0.40
    filled
    0.39
    련
    0.39
    izielle
    0.38
     الرياضيه
    0.37
    Listen
    0.37
    Activations Density 0.284%

    No Known Activations