© 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. 111545
    Prev
    Next
    INDEX
    Explanations

    references to paternal relationships and the celebration of fatherhood

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

    father or dad

    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
     Mother
    -0.65
     MOTHER
    -0.58
    Mother
    -0.57
    mother
    -0.56
    clientY
    -0.56
     mother
    -0.54
     queen
    -0.53
    addGap
    -0.53
     gynhyrchwyd
    -0.50
    queen
    -0.49
    POSITIVE LOGITS
     father
    1.93
     fathers
    1.73
    father
    1.66
    Father
    1.65
     dad
    1.64
     Father
    1.63
     FATHER
    1.57
    Dad
    1.56
     dads
    1.54
     père
    1.53
    Activations Density 0.078%

    No Known Activations