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. 1-GEMMASCOPE-RES-16K
    6. 6089
    Prev
    Next
    INDEX
    Explanations

    references to conferences and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CellValue
    -0.56
     доб
    -0.52
    setForeground
    -0.52
     pâte
    -0.51
    opat
    -0.50
     yeux
    -0.49
    مرار
    -0.49
     jual
    -0.49
    documentElement
    -0.49
    execSQL
    -0.48
    POSITIVE LOGITS
     conference
    4.60
     Conference
    4.35
    Conference
    4.13
     conferences
    3.93
    conference
    3.86
     CONFERENCE
    3.84
     Conferences
    3.59
     Konferenz
    2.89
     conférence
    2.78
     konfer
    2.72
    Activations Density 0.055%

    No Known Activations