© 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. 10876
    Prev
    Next
    INDEX
    Explanations

    structured data, definitions, and parameters related to computational functions or algorithms

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

    "AD" or "ad" (possibly followed by other characters)

    np_acts-logits-general · gemini-2.0-flash

    AD, adapter, adherence, address

    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
     Marty
    -0.66
     Estelle
    -0.65
    Marty
    -0.64
     PGC
    -0.62
     Germ
    -0.59
    CloseOperation
    -0.58
    Germ
    -0.56
    SequentialGroup
    -0.55
     Cler
    -0.55
     mergeFrom
    -0.55
    POSITIVE LOGITS
     Ad
    1.94
     AD
    1.89
    Ad
    1.80
    AD
    1.66
     ad
    1.65
     adapter
    1.56
     Aden
    1.51
     Adapter
    1.50
    ad
    1.47
     Adler
    1.46
    Activations Density 0.351%

    No Known Activations