© 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. 35-GEMMASCOPE-RES-16K
    6. 7683
    Prev
    Next
    INDEX
    Explanations

    references to mathematical concepts and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rumah
    -0.51
    inheritDoc
    -0.47
    ParseTree
    -0.46
    ToBounds
    -0.46
    onAttach
    -0.46
     محفوظة
    -0.46
     MyBatis
    -0.46
     TextAlign
    -0.44
    THISDAY
    -0.43
    onViewCreated
    -0.43
    POSITIVE LOGITS
    țe
    0.38
    ViewFeatures
    0.38
    RTDA
    0.36
    siune
    0.36
     exemplo
    0.36
     historischen
    0.36
    dientemente
    0.35
    érons
    0.35
    iseite
    0.35
    URRED
    0.35
    Activations Density 0.275%

    No Known Activations