© 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. 8828
    Prev
    Next
    INDEX
    Explanations

    references to health-related factors and entities

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

    academic citations and punctuation marks, particularly commas.

    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
    awaiter
    -0.52
    __);
    -0.44
    glä
    -0.43
    classnames
    -0.42
    usermodel
    -0.41
     通販
    -0.41
     HAMILTON
    -0.41
    брь
    -0.40
     HUNTER
    -0.40
     HUS
    -0.40
    POSITIVE LOGITS
    parsedMessage
    0.45
    EDEFAULT
    0.42
    他にも
    0.40
     يتيمه
    0.39
     besides
    0.39
    aarrggbb
    0.39
     censiti
    0.39
    RenderAtEndOf
    0.38
    他に
    0.37
    IUrlHelper
    0.37
    Activations Density 0.149%

    No Known Activations