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-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53004
    Prev
    Next
    INDEX
    Explanations

    quotation marks and other punctuation indicating speech or dialogue

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

    medical diagnosis and scientific data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DOCTYPE
    -0.65
    ****************
    -0.59
     mes
    -0.53
    furt
    -0.52
     Borg
    -0.51
    ================
    -0.48
    ————————————————
    -0.48
     Bre
    -0.48
     g
    -0.48
     Chan
    -0.47
    POSITIVE LOGITS
     nahilalakip
    0.92
    StructEnd
    0.84
    Rohy
    0.83
    tagHelperRunner
    0.77
    kepada
    0.76
    NameInMap
    0.75
     autorytatywna
    0.73
    )");
    
    0.72
    BeginContext
    0.71
    rizona
    0.71
    Activations Density 0.074%

    No Known Activations