Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 6783
    Prev
    Next
    INDEX
    Explanations

    references to stereotypes and misconceptions about Native Americans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.56
    ثيق
    -0.51
    LEADING
    -0.50
    ciation
    -0.46
     TestBed
    -0.46
    AndEndTag
    -0.46
    racene
    -0.46
     Twist
    -0.45
     Showing
    -0.45
    fok
    -0.45
    POSITIVE LOGITS
     utafitiHapana
    0.74
     صوتيه
    0.73
     magically
    0.61
     somehow
    0.56
    stateProvider
    0.55
    ReusableCell
    0.55
     fleste
    0.54
    scriptId
    0.54
    ConstraintMaker
    0.53
     tropicales
    0.53
    Activations Density 0.372%

    No Known Activations