© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 15599
    Prev
    Next
    INDEX
    Explanations

    occurrences of probabilities and chance in relation to outcomes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    probability or likelihood

    np_acts-logits-general · gemini-2.0-flash

    probability and odds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Portail
    -0.63
     betweenstory
    -0.50
     transfieras
    -0.50
     Affiliations
    -0.48
    BufferException
    -0.47
     AssemblyCompany
    -0.47
    antMatchers
    -0.47
    fortawesome
    -0.46
    tagHelperRunner
    -0.46
    NOPQRST
    -0.45
    POSITIVE LOGITS
     chances
    2.83
     Chances
    2.52
     probability
    2.48
     likelihood
    2.44
    Chances
    2.36
     odds
    2.30
     chance
    2.22
     probabilities
    2.09
    probability
    2.09
     Probability
    2.03
    Activations Density 0.953%

    No Known Activations