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. 13-GEMMASCOPE-RES-16K
    6. 6605
    Prev
    Next
    INDEX
    Explanations

    numbers and numerical data references within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.67
    例句
    -0.56
     chal
    -0.52
     spieg
    -0.52
    chal
    -0.52
    timewa
    -0.51
    nię
    -0.51
    zionali
    -0.49
    ResponseEntity
    -0.47
    뜸
    -0.46
    POSITIVE LOGITS
    setVerticalGroup
    0.76
    ViewFeatures
    0.74
    Datuak
    0.68
     GetEnumerator
    0.65
    writeFieldEnd
    0.65
    ⓧ
    0.63
     AssemblyTitle
    0.63
    ArrowToggle
    0.63
    oa̍t
    0.62
    writeField
    0.62
    Activations Density 0.212%

    No Known Activations