© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 116309
    Prev
    Next
    INDEX
    Explanations

    references to URL or web-related terms, specifically focusing on the "medium" attribute

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

    medium

    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
    waltung
    -0.50
    BufferException
    -0.42
    GOTREF
    -0.40
    vartis
    -0.40
    culously
    -0.39
     GetEnumerator
    -0.39
    asList
    -0.39
     AFL
    -0.38
     Cranes
    -0.38
    etsk
    -0.37
    POSITIVE LOGITS
    Medium
    2.78
    medium
    2.77
     Medium
    2.67
     medium
    2.38
     MEDIUM
    2.31
    MEDIUM
    2.22
     mediums
    1.63
     mediano
    1.10
     mediu
    1.04
     mittel
    0.96
    Activations Density 0.003%

    No Known Activations