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. 8-GEMMASCOPE-RES-16K
    6. 5875
    Prev
    Next
    INDEX
    Explanations

    words related to feelings of pride and embarrassment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMailer
    -0.74
    клопе
    -0.73
    HandlerContext
    -0.72
    TagMode
    -0.69
    transQ
    -0.68
    DeleteBehavior
    -0.67
    )++;
    -0.67
    CloseOperation
    -0.65
     pleaſure
    -0.64
    脚注の使い方
    -0.62
    POSITIVE LOGITS
     proud
    0.58
    AlterField
    0.55
     feature
    0.53
     pride
    0.53
     orgull
    0.51
    proud
    0.50
     boast
    0.48
    feature
    0.48
     features
    0.47
    SourceChecksum
    0.47
    Activations Density 0.168%

    No Known Activations