Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5340
    Prev
    Next
    INDEX
    Explanations

    elements related to user input and interactions within a web interface

    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
    InputBorder
    -0.57
     lizenzfreie
    -0.44
     CURLOPT
    -0.40
    Tikang
    -0.39
    ۜ
    -0.39
    SourceChecksum
    -0.39
    medriver
    -0.36
    /**
    -0.36
    Metro
    -0.36
    ICATED
    -0.36
    POSITIVE LOGITS
     ModelExpression
    0.59
     bileklik
    0.52
     kolye
    0.52
     męska
    0.51
     femininas
    0.50
     manzanas
    0.48
    décoration
    0.46
    最快更新
    0.46
    pulseira
    0.46
     damska
    0.45
    Activations Density 0.210%

    No Known Activations