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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 1810
    Prev
    Next
    INDEX
    Explanations

    terms related to research and bias

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

    preceding or related to "bias"

    np_acts-logits-general · gemini-2.0-flash

    bias and avoiding bias

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    AddTagHelper
    -0.57
     Inscrivez
    -0.54
    expandindo
    -0.54
    ChildScrollView
    -0.53
    ConstraintMaker
    -0.52
     hidrá
    -0.50
    ereum
    -0.50
     FetchType
    -0.49
     réguli
    -0.48
     PublicKey
    -0.48
    POSITIVE LOGITS
     bias
    2.09
     biased
    1.93
     biases
    1.72
     Bias
    1.65
    bias
    1.58
    biased
    1.57
    Bias
    1.49
    biases
    1.31
    BIAS
    1.29
     favou
    1.12
    Activations Density 0.701%

    No Known Activations