© 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. 18-GEMMASCOPE-RES-16K
    11. 1594
    Prev
    Next
    INDEX
    Explanations

    phrases indicating global or regional prominence and recognition

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

    Following superlative adjectives

    np_acts-logits-general · gemini-2.0-flash

    superlative adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.75
     transfieras
    -0.65
    AnchorStyles
    -0.63
    Enllaços
    -0.54
     kasarigan
    -0.49
     jednotliv
    -0.47
    bių
    -0.47
     vant
    -0.47
    bish
    -0.47
    ike
    -0.47
    POSITIVE LOGITS
     longest
    1.39
     fastest
    1.33
     cleanest
    1.32
     largest
    1.27
     widest
    1.22
     strongest
    1.21
     most
    1.21
     slowest
    1.20
     shortest
    1.20
     prettiest
    1.17
    Activations Density 0.156%

    No Known Activations