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. 25-GEMMASCOPE-RES-16K
    6. 10418
    Prev
    Next
    INDEX
    Explanations

    expressions related to feelings of discomfort and the need for guidance in social or personal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     both
    -0.71
     Various
    -0.69
     not
    -0.68
    而不是
    -0.66
     plutôt
    -0.66
     various
    -0.66
    Various
    -0.65
     autorytatywna
    -0.65
    而非
    -0.64
    χι
    -0.63
    POSITIVE LOGITS
     nor
    2.58
     anymore
    2.23
    nor
    1.85
     anything
    1.74
     anywhere
    1.56
     nici
    1.54
    anything
    1.54
     any
    1.52
     whatsoever
    1.49
    Nor
    1.48
    Activations Density 2.293%

    No Known Activations