© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1354
    Prev
    Next
    INDEX
    Explanations

    expressions of positivity or approval

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

    Following the word "good"

    np_acts-logits-general · gemini-2.0-flash

    good descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ilha
    -0.48
    Ashlee
    -0.44
     transfer
    -0.43
    StreamWriter
    -0.42
     cadeia
    -0.42
     Wraith
    -0.42
    transfer
    -0.41
    PathVariable
    -0.41
     transferência
    -0.41
     Isla
    -0.40
    POSITIVE LOGITS
    Good
    1.27
     Good
    1.23
     GOOD
    1.20
    good
    1.20
     good
    1.17
    GOOD
    1.14
     Хоро
    0.88
    Хороший
    0.87
     bonnes
    0.86
     buen
    0.85
    Activations Density 0.080%

    No Known Activations