© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 6521
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "m" and its variations, particularly in connections to masculinity

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

    starting with "M" followed by a lowercase letter

    np_acts-logits-general · gemini-2.0-flash

    ma, m, Man

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.34
     suces
    -0.33
    styleType
    -0.33
     aside
    -0.33
     Kon
    -0.31
    ंडल
    -0.31
     Richter
    -0.31
     fire
    -0.31
    ppon
    -0.31
    GIVEREF
    -0.31
    POSITIVE LOGITS
     MCM
    0.59
     getModel
    0.57
     matri
    0.57
     mijne
    0.56
    +#+#
    0.56
    MCM
    0.56
     Marquette
    0.55
    MarshalTo
    0.54
     purpoſe
    0.54
     miſ
    0.54
    Activations Density 0.393%

    No Known Activations