© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9524
    Prev
    Next
    INDEX
    Explanations

    terms related to fixed structures or configurations, especially in computational or engineering contexts

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

    "Fixed" or words associated with "fixed"

    np_acts-logits-general · gemini-2.0-flash

    fixed software and aircraft parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     secours
    -0.39
    вель
    -0.37
     płyn
    -0.36
    graceful
    -0.35
     Hanson
    -0.35
     zel
    -0.34
     Sinclair
    -0.34
    Lato
    -0.34
     */
    -0.33
     experienced
    -0.32
    POSITIVE LOGITS
     fixing
    0.95
     fix
    0.94
    Fix
    0.91
     Fix
    0.90
     fixation
    0.89
     fixes
    0.88
     FIX
    0.86
    Fixing
    0.85
    FIX
    0.85
    fixing
    0.84
    Activations Density 0.201%

    No Known Activations