© 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. 22-GEMMASCOPE-RES-16K
    11. 8265
    Prev
    Next
    INDEX
    Explanations

    actions or commands related to creating or performing tasks

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

    "Make" followed by "sure"

    np_acts-logits-general · gemini-2.0-flash

    make sure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.68
    enterOuterAlt
    -0.66
    principalColumn
    -0.62
     références
    -0.58
    rawDesc
    -0.58
    reactstrap
    -0.57
    Personendaten
    -0.57
     grecque
    -0.56
     trưởng
    -0.55
    々木
    -0.55
    POSITIVE LOGITS
     sure
    0.98
     SURE
    0.66
     Sure
    0.64
     متعلقه
    0.59
     propOrder
    0.58
    Sure
    0.55
     note
    0.55
    sure
    0.54
     initComponents
    0.51
    Aholisi
    0.51
    Activations Density 0.114%

    No Known Activations