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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14318
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and structure related to function calls in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    wpi
    -0.60
     presidential
    -0.50
    gameserver
    -0.48
    HomeAsUpEnabled
    -0.47
     PropertyChanged
    -0.46
    ธิ
    -0.46
    skri
    -0.45
     Presidential
    -0.45
    tagext
    -0.44
    URLException
    -0.43
    POSITIVE LOGITS
    KommentareTeilen
    0.66
    íncia
    0.59
    ientí
    0.58
    Παραπομπές
    0.58
     Basel
    0.56
    Например
    0.55
    bcryptjs
    0.55
    abancı
    0.55
    URIComponent
    0.54
    encodeWith
    0.54
    Activations Density 0.048%

    No Known Activations