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. 9-GEMMASCOPE-RES-16K
    6. 3752
    Prev
    Next
    INDEX
    Explanations

    characters or syntax related to code formatting and structure

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

    Code snippets and special characters

    np_acts-logits-general · gemini-2.0-flash

    '_

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.55
    XmlAccessorType
    -0.52
     виправивши
    -0.50
    protoimpl
    -0.47
    '])){
    
    -0.44
     INTERESAR
    -0.42
    
    -0.41
    ")){
    
    -0.41
    yntaxException
    -0.40
     pitä
    -0.40
    POSITIVE LOGITS
     Sentin
    0.45
    ondissement
    0.45
    InputTagHelper
    0.43
    днако
    0.41
     Batal
    0.41
    copyWith
    0.40
    .'/
    0.38
    +"'
    0.37
     TextAppearance
    0.36
     alfo
    0.36
    Activations Density 1.044%

    No Known Activations