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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3272
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate searching or looking for information

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

    "Look for" phrase

    np_acts-logits-general · gemini-2.0-flash

    searching for something

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Deshalb
    -0.37
     perfeitamente
    -0.36
     bürger
    -0.35
    Perfectly
    -0.35
     seamlessly
    -0.35
     gezond
    -0.34
     largas
    -0.33
     απο
    -0.33
     perfettamente
    -0.33
    reg
    -0.32
    POSITIVE LOGITS
    checkFor
    0.62
    寻找
    0.60
     cherchés
    0.60
    WithIOException
    0.59
     detect
    0.59
    rrggbb
    0.59
    尋找
    0.59
     detecting
    0.58
     Detect
    0.57
     lookout
    0.56
    Activations Density 0.337%

    No Known Activations