© 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. 10-GEMMASCOPE-RES-16K
    6. 6447
    Prev
    Next
    INDEX
    Explanations

    historical or architectural significance in a location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.56
     Arora
    -0.52
    TRAILING
    -0.52
    Tikang
    -0.50
    ValueStyle
    -0.49
    awtextra
    -0.48
    ViewImports
    -0.47
     ujednoznacz
    -0.47
    natur
    -0.47
    XmlAccessType
    -0.46
    POSITIVE LOGITS
     built
    0.99
     construction
    0.96
     building
    0.94
     Built
    0.88
    built
    0.86
    Built
    0.85
     constructed
    0.84
     Building
    0.82
     buildings
    0.81
     builders
    0.80
    Activations Density 0.358%

    No Known Activations