© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3896
    Prev
    Next
    INDEX
    Explanations

    instances of the word "operate" and its variations, indicating a focus on operational contexts

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

    "Operate" and its inflections

    np_acts-logits-general · gemini-2.0-flash

    operating in or under

    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
    PerformLayout
    -0.65
     endforeach
    -0.63
    Tup
    -0.59
    ایج
    -0.56
     rápidas
    -0.56
     gedaan
    -0.55
     pétrole
    -0.55
    ตาย
    -0.54
     meille
    -0.53
    getAmount
    -0.53
    POSITIVE LOGITS
     operating
    0.83
     functioning
    0.80
    Operating
    0.80
     Operating
    0.78
     operate
    0.78
     operates
    0.75
     operated
    0.75
    operating
    0.74
     functions
    0.74
    providedIn
    0.71
    Activations Density 0.212%

    No Known Activations