© 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. 77918
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific scientific or medical context involving 'gla' related elements, possibly referring to Glatiramer Acetate or similar compounds

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

    words starting with gla

    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
     Perseus
    -0.51
     bobby
    -0.50
     Opus
    -0.50
     ROK
    -0.50
     belongings
    -0.50
    ornis
    -0.50
    ucket
    -0.50
     securities
    -0.49
    unum
    -0.48
    ponses
    -0.48
    POSITIVE LOGITS
     Gla
    2.33
    Gla
    2.09
     gla
    1.91
    gla
    1.58
     GLA
    1.43
    GLA
    1.41
     Glaze
    1.31
     glazing
    1.25
     glaze
    1.19
    glazed
    1.15
    Activations Density 0.005%

    No Known Activations