© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 8759
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to UI component layout and properties

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

    Code containing parentheses

    np_acts-logits-general · gemini-2.0-flash

    code punctuation like parens, colons, equals

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     виправивши
    -0.67
    évaluateur
    -0.57
    adpleegd
    -0.54
     OFDb
    -0.54
    mişti
    -0.54
    󠁴
    -0.53
     ErrIntOverflow
    -0.52
     beginnetje
    -0.52
     betweenstory
    -0.51
     hinaus
    -0.49
    POSITIVE LOGITS
    InstanceState
    0.57
     Incentives
    0.55
     incentives
    0.54
    chner
    0.52
     academically
    0.52
     Fuku
    0.51
     musically
    0.51
    pann
    0.51
     pleins
    0.50
     seaborn
    0.50
    Activations Density 0.058%

    No Known Activations