© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8458
    Prev
    Next
    INDEX
    Explanations

    conjunctions and other linking words in the text

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

    Imperative verbs (remember, contact, consider, try)

    np_acts-logits-general · gemini-2.0-flash

    instructions or requests

    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
    OGND
    -0.58
     snippetHide
    -0.54
    存于互联网档案馆
    -0.51
     intStringLen
    -0.50
     tartalomajánló
    -0.49
     auroit
    -0.48
     cherchés
    -0.48
    verwijspagina
    -0.47
     avoient
    -0.45
     agrí
    -0.44
    POSITIVE LOGITS
     remember
    1.57
     don
    1.53
     please
    1.49
     consider
    1.43
     try
    1.41
     keep
    1.25
     check
    1.25
     watch
    1.20
     ask
    1.19
     let
    1.18
    Activations Density 0.436%

    No Known Activations