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. 20-GEMMASCOPE-RES-16K
    6. 15650
    Prev
    Next
    INDEX
    Explanations

    characters or symbols that indicate specific variables or parameters

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

    Characters preceding parentheses

    np_acts-logits-general · gemini-2.0-flash

    parenthesized labels or parameters

    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
    '])->
    -0.69
    ########.
    -0.67
     cinto
    -0.61
     _,
    -0.59
    èdia
    -0.56
    '],$
    -0.55
    تقاوى
    -0.55
    ::_('
    -0.54
    Geplaatst
    -0.54
     /\.
    -0.53
    POSITIVE LOGITS
    ưỡi
    0.54
     تانيه
    0.53
    плуата
    0.53
     désolés
    0.51
    ítmény
    0.50
    windowFixed
    0.50
    neſs
    0.48
    InView
    0.48
     NTP
    0.47
    igenschaften
    0.45
    Activations Density 0.189%

    No Known Activations