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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14438
    Prev
    Next
    INDEX
    Explanations

    information about football players and their careers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     typelib
    -0.69
    makeConstraints
    -0.59
    fört
    -0.54
     jspb
    -0.53
     <<<<<<<<<<<<<<
    -0.53
    TokenNameLBRACE
    -0.52
     delegado
    -0.52
    NameInMap
    -0.52
     '\\;'
    -0.52
     resourceCulture
    -0.51
    POSITIVE LOGITS
     rival
    0.50
     franchise
    0.40
     coach
    0.38
     overseas
    0.36
     [_
    0.36
     club
    0.36
     big
    0.35
     affiliate
    0.35
    '},
    
    0.35
    ViewFeatures
    0.35
    Activations Density 0.259%

    No Known Activations