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 Post
    5. 12-GEMMASCOPE-RES-1M
    6. 153
    Prev
    Next
    INDEX
    Explanations

    references to South and North Korea, particularly in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.69
    ?>">
    -0.64
    InputTagHelper
    -0.62
    Története
    -0.61
    ativement
    -0.59
     pageContext
    -0.58
    MessageTagHelper
    -0.57
    matchCondition
    -0.57
    FormTagHelper
    -0.56
     незавершена
    -0.56
    POSITIVE LOGITS
    ngrx
    0.51
     disparu
    0.48
    nestjs
    0.47
    GTCX
    0.47
    órmulas
    0.46
    enschappelijke
    0.45
    مود
    0.44
    WebpackPlugin
    0.43
     diman
    0.43
    ถม
    0.42
    Activations Density 0.000%

    No Known Activations