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 - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7503
    Prev
    Next
    INDEX
    Explanations

    Java annotations related to serialization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeText
    -0.73
    istoitu
    -0.73
    loem
    -0.65
    Vidi
    -0.61
    elux
    -0.60
     nonatomic
    -0.58
    խ
    -0.57
     Poincar
    -0.57
    ölkerung
    -0.55
    diano
    -0.54
    POSITIVE LOGITS
     jsPsych
    2.24
    SourceChecksum
    1.20
    GeneratedMessage
    1.09
    tagext
    1.03
    sizeCache
    1.02
    HasColumnType
    1.01
    addCriterion
    0.99
    OrBuilder
    0.98
    TokenName
    0.91
    setHorizontal
    0.88
    Activations Density 0.035%

    No Known Activations