© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 1566
    Prev
    Next
    INDEX
    Explanations

    references to racial identity issues and accusations surrounding race relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.55
    FormState
    -0.49
    횟
    -0.49
    menistan
    -0.48
     FishBase
    -0.47
    didSet
    -0.46
     Cunha
    -0.45
    arakhand
    -0.44
     Turkmenistan
    -0.44
    GridItem
    -0.43
    POSITIVE LOGITS
     racial
    2.03
     racism
    2.00
     Racial
    1.87
     racist
    1.86
     race
    1.85
     racially
    1.81
     Racism
    1.79
    racial
    1.74
    Racism
    1.72
     Race
    1.72
    Activations Density 1.454%

    No Known Activations