© 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. 24-GEMMASCOPE-RES-16K
    11. 10622
    Prev
    Next
    INDEX
    Explanations

    words that convey positivity or good quality

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

    "Good"

    np_acts-logits-general · gemini-2.0-flash

    common phrases starting with Good

    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
     cadeia
    -0.52
     ilha
    -0.48
    unlink
    -0.46
     montanha
    -0.42
     Martel
    -0.42
     bezit
    -0.41
     transferência
    -0.41
    fling
    -0.40
     vekt
    -0.40
    xicity
    -0.39
    POSITIVE LOGITS
    Good
    1.10
     Good
    1.08
     GOOD
    1.01
    GOOD
    0.96
    good
    0.96
     good
    0.89
     Goodwin
    0.77
     Goodman
    0.75
    Хороший
    0.74
     gud
    0.72
    Activations Density 0.091%

    No Known Activations