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. 11-GEMMASCOPE-RES-16K
    6. 1796
    Prev
    Next
    INDEX
    Explanations

    references to mechanisms of accountability and recognition within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leaner
    -0.61
     Cæsar
    -0.60
    下载附件
    -0.59
     purpoſe
    -0.57
     étoient
    -0.57
    yyj
    -0.55
    parsedMessage
    -0.55
     feeder
    -0.55
     Chriftian
    -0.55
     elettrico
    -0.53
    POSITIVE LOGITS
    ConstraintMaker
    0.59
     Daarom
    0.57
     Derfor
    0.56
    RegistryLite
    0.53
     sogar
    0.53
    */}
    0.53
     even
    0.53
     renom
    0.52
    なのか
    0.49
    あえて
    0.49
    Activations Density 0.296%

    No Known Activations