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. 16184
    Prev
    Next
    INDEX
    Explanations

    decorative elements and details in descriptions

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

    relating to decoration or ornamentation

    np_acts-logits-general · gemini-2.0-flash

    decorative elements and adornments

    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
     للمعارف
    -0.64
    providedIn
    -0.48
    enterOuterAlt
    -0.47
     enfans
    -0.47
    lück
    -0.44
     charbon
    -0.43
     <<<<<<<<<<<<<<
    -0.42
    المناصب
    -0.42
    (!__
    -0.42
     siebie
    -0.41
    POSITIVE LOGITS
     decoration
    1.30
     decorations
    1.30
     decorative
    1.26
     ornamentation
    1.19
     decorated
    1.10
     decorating
    1.10
     embell
    1.09
     decorate
    1.08
     ornate
    1.07
     ornaments
    1.02
    Activations Density 0.136%

    No Known Activations