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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 1484
    Prev
    Next
    INDEX
    Explanations

    occurrences of programming functions related to reading and writing data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    жели
    -0.54
    neighbours
    -0.50
     gewä
    -0.50
     orientación
    -0.49
    mals
    -0.49
     Sykes
    -0.48
    förs
    -0.48
    setSuccess
    -0.48
     Mullins
    -0.47
     feil
    -0.47
    POSITIVE LOGITS
    write
    1.66
    Write
    1.11
     write
    1.02
    enumi
    1.00
     kasarigan
    0.95
    WriteLiteral
    0.90
    writes
    0.87
    writing
    0.85
    WRITE
    0.84
     Write
    0.84
    Activations Density 0.062%

    No Known Activations