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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 81293
    Prev
    Next
    INDEX
    Explanations

    references to build or configuration files and their statuses

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

    build and build success

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     senhora
    -0.47
    WidgetItem
    -0.44
     namorados
    -0.42
    不说
    -0.42
    querySelectorAll
    -0.41
     keselamatan
    -0.41
     vítimas
    -0.41
     sereia
    -0.41
    othermal
    -0.41
     toalha
    -0.40
    POSITIVE LOGITS
     Build
    1.16
    Build
    1.13
     BUILD
    1.05
    build
    1.02
     build
    1.01
    BUILD
    0.93
    Builds
    0.83
     Building
    0.81
    Building
    0.80
     Built
    0.79
    Activations Density 0.011%

    No Known Activations