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. 1776
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons and relationships between entities

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

    preceding "other" (or its variations)

    np_acts-logits-general · gemini-2.0-flash

    other words and phrases

    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
    cloudflare
    -0.44
    prepareStatement
    -0.43
    ритори
    -0.43
    WriteBarrier
    -0.42
     <=",
    -0.42
    ometre
    -0.41
    setViewName
    -0.41
    writeField
    -0.41
    netbeans
    -0.41
     PARSER
    -0.40
    POSITIVE LOGITS
     other
    4.20
    other
    3.69
    Other
    3.27
     Other
    3.22
    autres
    3.21
     autres
    3.15
     otros
    3.12
     OTHER
    3.10
     otras
    3.04
     autre
    3.00
    Activations Density 4.329%

    No Known Activations