© 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. 4070
    Prev
    Next
    INDEX
    Explanations

    instructions or steps related to a process or method

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

    programming-related instructions and actions like method calls, code modifications, and problem-solving steps.

    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
     ब्रेकडाउन
    -0.40
    BeginInit
    -0.35
    oneofs
    -0.34
    AddWithValue
    -0.34
     Selanjutnya
    -0.34
     répar
    -0.32
     calorías
    -0.31
     विश्वसनीयता
    -0.31
    PropertyChanging
    -0.31
    /></
    -0.31
    POSITIVE LOGITS
    tonode
    0.47
    urismo
    0.45
    StoryboardSegue
    0.44
     Laredo
    0.43
    erals
    0.43
    ubber
    0.43
     bidet
    0.43
    bilità
    0.43
     heavier
    0.43
    WithIOException
    0.42
    Activations Density 0.528%

    No Known Activations