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. 20-GEMMASCOPE-RES-16K
    6. 15870
    Prev
    Next
    INDEX
    Explanations

    structured data elements and attributes related to visual representation or user interface components

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

    Strings being added or trimmed

    np_acts-logits-general · gemini-2.0-flash

    text display operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MotionEvent
    -0.68
    addCriterion
    -0.63
     @"/
    -0.60
    colgroup
    -0.60
    RenderAtEndOf
    -0.59
    SetBool
    -0.59
    #+#
    -0.58
     SearchView
    -0.57
     disambiguazione
    -0.56
     Partagez
    -0.56
    POSITIVE LOGITS
     text
    1.19
     Text
    1.01
     texts
    0.97
     font
    0.94
    文本
    0.93
    Text
    0.92
     teks
    0.92
    text
    0.91
     texto
    0.90
     typography
    0.88
    Activations Density 0.229%

    No Known Activations