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. 16299
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing precision or specificity in descriptions

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

    "exactly" or similar words

    np_acts-logits-general · gemini-2.0-flash

    exactly or precisely

    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
    -------
    -0.54
    complexContent
    -0.52
    FLD
    -0.50
     realmente
    -0.49
    umbar
    -0.48
    orter
    -0.46
    存于互联网档案馆
    -0.46
     truly
    -0.46
    addCriterion
    -0.45
    depre
    -0.45
    POSITIVE LOGITS
     opposite
    0.51
     disambiguazione
    0.45
     Gegenteil
    0.45
     same
    0.43
    opposite
    0.42
     censiti
    0.42
    Exactly
    0.42
     Мексичка
    0.41
     Exactly
    0.40
    夠
    0.40
    Activations Density 0.101%

    No Known Activations