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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15846
    Prev
    Next
    INDEX
    Explanations

    discussions about personal reflections on experiences and places that evoke feelings of belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "There is/was something"

    np_acts-logits-general · gemini-2.0-flash

    there's something about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     témoig
    -0.65
    GEBURTSDATUM
    -0.63
     queſta
    -0.60
    +#+#
    -0.59
    parsedMessage
    -0.58
    contentLoaded
    -0.58
     indígen
    -0.55
    RenderAtEndOf
    -0.55
     YellowPages
    -0.55
    IsMutable
    -0.54
    POSITIVE LOGITS
     somehow
    1.19
     Somehow
    1.00
    Somehow
    0.97
     something
    0.88
    有一种
    0.79
     irgendwie
    0.79
     kind
    0.75
     sort
    0.75
     quelque
    0.73
    something
    0.73
    Activations Density 0.354%

    No Known Activations