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. 15873
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements in code snippets

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

    Code syntax or special characters

    np_acts-logits-general · gemini-2.0-flash

    code syntax and types

    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
     disambiguazione
    -0.90
    rungsseite
    -0.79
     ujednoznacz
    -0.74
    GEBURTSDATUM
    -0.74
     typelib
    -0.69
     cherchés
    -0.67
     lenker
    -0.66
    DispatchToProps
    -0.65
     MainAxisSize
    -0.63
     ProtoMessage
    -0.63
    POSITIVE LOGITS
    뀐
    0.49
    â
    0.47
    un
    0.45
    nos
    0.45
    unk
    0.44
    cin
    0.43
     Pelleg
    0.43
    뀔
    0.43
    de
    0.41
    fa
    0.41
    Activations Density 0.115%

    No Known Activations