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. 2151
    Prev
    Next
    INDEX
    Explanations

    the word "most" in various contexts

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

    Follows "most" and precedes an adjective

    np_acts-logits-general · gemini-2.0-flash

    superlatives

    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
     noDo
    -0.87
    OGND
    -0.84
    MigrationBuilder
    -0.82
    TypedDataSet
    -0.79
     فريبيس
    -0.77
    Autoritní
    -0.74
    very
    -0.72
    parsedMessage
    -0.72
    awtextra
    -0.71
    ArrowToggle
    -0.69
    POSITIVE LOGITS
     important
    0.71
     recent
    0.66
     likely
    0.64
     wanted
    0.52
     importantly
    0.52
     certainly
    0.52
     recently
    0.50
     sought
    0.49
     feared
    0.49
     effective
    0.49
    Activations Density 0.101%

    No Known Activations