© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 112149
    Prev
    Next
    INDEX
    Explanations

    mentions of bias in various contexts

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

    bias in statistics or algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.52
    -//
    -0.44
    SqlParameter
    -0.41
    interesting
    -0.41
    Castell
    -0.40
     Nok
    -0.39
     ویکی‌پدی
    -0.39
     XNUMX
    -0.38
     great
    -0.37
    Http
    -0.37
    POSITIVE LOGITS
     Bias
    1.33
     bias
    1.30
    bias
    1.22
    Bias
    1.17
     biases
    1.06
    BIAS
    1.04
     biased
    1.01
    biased
    0.94
    biases
    0.92
     Prejudice
    0.86
    Activations Density 0.022%

    No Known Activations