© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 10728
    Prev
    Next
    INDEX
    Explanations

    structured data, tags, or references related to technical documentation, coding, or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ists
    -0.51
    ist
    -0.44
    Referências
    -0.43
    udert
    -0.42
    wdata
    -0.41
    angerschaft
    -0.41
     épo
    -0.41
    <eos>
    -0.41
    が必要です
    -0.40
    ızı
    -0.40
    POSITIVE LOGITS
    ]")]
    0.52
     forState
    0.52
    providedIn
    0.51
    Ӕ
    0.51
     endregion
    0.47
     吋
    0.46
    outWeight
    0.45
    '][$
    0.45
     AssemblyProduct
    0.44
    __(/*!
    0.44
    Activations Density 1.864%

    No Known Activations