© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2639
    Prev
    Next
    INDEX
    Explanations

    references to marginalized gender identities and sexual orientations

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

    Identity categories and demographic characteristics, particularly those related to marginalized or underrepresented groups.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    الحياه
    -0.68
    IndentedString
    -0.64
    MessageOf
    -0.62
    endcsname
    -0.60
     Италијани
    -0.59
    +#+
    -0.57
    RUnlock
    -0.51
     يتيمه
    -0.50
    webElementXpaths
    -0.50
    ">//
    -0.49
    POSITIVE LOGITS
     transgender
    1.14
     gender
    1.07
     trans
    1.01
    gender
    0.94
     Gender
    0.93
    Gender
    0.88
     pronouns
    0.87
    trans
    0.84
     Trans
    0.83
     bisexual
    0.78
    Activations Density 0.208%

    No Known Activations