© 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. 15-GEMMASCOPE-RES-16K
    6. 13195
    Prev
    Next
    INDEX
    Explanations

    phrases related to bias and its implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.56
    endpush
    -0.53
    Newswire
    -0.53
    basicConfig
    -0.53
     AllAfrica
    -0.49
    帖最后由
    -0.47
    archiviato
    -0.47
    UrlResolution
    -0.47
    OGND
    -0.47
     صوتيه
    -0.46
    POSITIVE LOGITS
    Например
    1.29
     Например
    1.26
    例如
    1.19
     например
    1.19
     esempio
    1.16
     Examples
    1.16
    比如
    1.14
     bijvoorbeeld
    1.12
     Example
    1.11
     उदाहरण
    1.11
    Activations Density 0.510%

    No Known Activations