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

    Neuronpedia

    APICircuit 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. 2326
    Prev
    Next
    INDEX
    Explanations

    actions related to giving, placing, or putting items in various contexts

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

    followed by prepositions or articles

    np_acts-logits-general · gemini-2.0-flash

    actions performed

    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
    .
    -0.41
    hasOwnProperty
    -0.40
     oczywiście
    -0.40
    :
    -0.39
     for
    -0.38
     hvordan
    -0.36
     tentu
    -0.36
     pentru
    -0.36
     rifer
    -0.36
     samoz
    -0.35
    POSITIVE LOGITS
    RenderAtEndOf
    1.04
    رشف
    0.89
    "]}
    0.88
    invokeLater
    0.87
    setVerticalGroup
    0.87
    \{\\
    0.86
     lenker
    0.84
    MessageTagHelper
    0.84
    قایناق‌لار
    0.82
    HasForeignKey
    0.82
    Activations Density 0.353%

    No Known Activations