© 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. 8341
    Prev
    Next
    INDEX
    Explanations

    terms related to assessment and evaluation processes

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

    Following "determine" or "determination"

    np_acts-logits-general · gemini-2.0-flash

    ascertaining facts or conditions

    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
     
    -0.71
     “
    -0.64
     F
    -0.59
     I
    -0.58
    arache
    -0.57
     van
    -0.55
     Red
    -0.54
    light
    -0.53
      
    -0.53
    words
    -0.53
    POSITIVE LOGITS
     auffi
    1.09
     Majefty
    1.07
     myſelf
    1.04
     Reſ
    1.04
     purpoſe
    1.04
     greateſt
    1.02
     Efq
    1.02
     faſt
    1.02
    parsedMessage
    0.99
    /**
    0.98
    Activations Density 0.095%

    No Known Activations