Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 25697
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or object-oriented programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الدراسه
    -0.60
    RTDA
    -0.48
    PreferredItem
    -0.48
     OMITBAD
    -0.48
    Демографія
    -0.46
    oa̍t
    -0.46
    WriteTagHelper
    -0.46
    HasAnnotation
    -0.45
     resourceCulture
    -0.44
    цездатний
    -0.43
    POSITIVE LOGITS
     pareil
    0.46
     Formen
    0.38
     likewise
    0.37
     mesmas
    0.36
     Bibel
    0.36
     '\\;'
    0.36
    iastes
    0.35
    ditto
    0.35
     SAME
    0.35
     musicales
    0.35
    Activations Density 0.056%

    No Known Activations