© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 114683
    Prev
    Next
    INDEX
    Explanations

    references to "Sand" in geographical or location contexts

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

    sand-

    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
     wireType
    -0.40
     Motive
    -0.37
    <h3>
    -0.37
     distinctive
    -0.36
     Woche
    -0.35
     frequency
    -0.34
    ırı
    -0.34
     Lira
    -0.34
     fratello
    -0.33
    ActivityCompat
    -0.33
    POSITIVE LOGITS
     Sand
    2.23
    Sand
    2.11
     SAND
    1.68
     sand
    1.63
    sand
    1.58
    SAND
    1.58
     Sandberg
    1.36
     Sanderson
    1.32
     Sands
    1.28
     Sandbox
    1.26
    Activations Density 0.008%

    No Known Activations