© 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. 5663
    Prev
    Next
    INDEX
    Explanations

    references to historical origins and timelines

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

    Referring to dates or dating

    np_acts-logits-general · gemini-2.0-flash

    dates back

    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
    providedIn
    -0.71
    ureusement
    -0.68
    gameserver
    -0.68
     الحره
    -0.64
     VIAF
    -0.64
    AndEndTag
    -0.64
     nakalista
    -0.58
    didSet
    -0.58
    featureID
    -0.57
    +#+#
    -0.57
    POSITIVE LOGITS
     dating
    2.05
     dates
    1.79
    dating
    1.71
     Dating
    1.63
     dated
    1.58
     date
    1.57
    Dating
    1.49
     Dates
    1.47
     remonte
    1.42
    dates
    1.39
    Activations Density 0.355%

    No Known Activations