© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6862
    Prev
    Next
    INDEX
    Explanations

    negation expressions or phrases that suggest something is not true

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

    "not" followed by adverbs/qualifiers

    np_acts-logits-general · gemini-2.0-flash

    not only

    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
    xtext
    -0.69
     AssemblyCulture
    -0.62
    MigrationBuilder
    -0.61
    Portail
    -0.58
    writeFieldEnd
    -0.57
    InputTagHelper
    -0.55
     candidatura
    -0.55
     alemanes
    -0.54
    ukone
    -0.54
     sưu
    -0.54
    POSITIVE LOGITS
     sure
    0.91
    withstanding
    0.85
     not
    0.76
     much
    0.65
     wanting
    0.65
     gonna
    0.64
     everyone
    0.64
     knowing
    0.62
     all
    0.62
     exactly
    0.62
    Activations Density 0.072%

    No Known Activations