© 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. 22-GEMMASCOPE-RES-16K
    6. 8957
    Prev
    Next
    INDEX
    Explanations

    questions and statements about actions and experiences

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

    "did" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    did you know

    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
     fortsatt
    -0.73
    Искәрмәләр
    -0.68
     derzeit
    -0.65
    woordig
    -0.64
    ChildScrollView
    -0.64
     RDA
    -0.63
     shouldBe
    -0.63
    σθαι
    -0.62
    stateMutability
    -0.62
    "},
    
    -0.61
    POSITIVE LOGITS
     previously
    0.93
     originally
    0.92
     did
    0.83
     ayer
    0.81
    did
    0.80
     recently
    0.79
     originalmente
    0.79
     précédemment
    0.78
     Previously
    0.77
    originally
    0.77
    Activations Density 0.163%

    No Known Activations