© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8885
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to engineering and medical device design

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

    Movement or shifting in position/time

    np_acts-logits-general · gemini-2.0-flash

    slight changes or directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    찮
    -0.35
     gospodar
    -0.33
     Large
    -0.33
    ់
    -0.32
     Schrift
    -0.31
     unlimited
    -0.31
     Gemeinschaft
    -0.30
     беспо
    -0.30
     Long
    -0.30
    Continuous
    -0.30
    POSITIVE LOGITS
     slightly
    1.02
    slightly
    0.95
    Slightly
    0.88
     légèrement
    0.88
     ligeramente
    0.87
     slight
    0.87
     Slightly
    0.86
     leggermente
    0.77
     Slight
    0.75
    Slight
    0.72
    Activations Density 0.902%

    No Known Activations