© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 42898
    Prev
    Next
    INDEX
    Explanations

    patterns indicating gender differences and likelihoods in various contexts

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

    comparisons of likelihood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.47
    UrlResolution
    -0.46
     uLocal
    -0.44
    )_/¯
    -0.44
    Aiheesta
    -0.43
     Deeper
    -0.43
    httphttps
    -0.42
     AssemblyVersion
    -0.41
     disambiguazione
    -0.38
     verz
    -0.37
    POSITIVE LOGITS
     likely
    1.34
     likelihood
    1.22
    likely
    1.21
     Likely
    1.16
    Likely
    1.12
     unlikely
    1.05
    likelihood
    1.02
    Likelihood
    1.00
     Likelihood
    0.97
     probability
    0.91
    Activations Density 0.211%

    No Known Activations