© 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. 13283
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluation and assessment

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

    Preceding intensifiers or degree modifiers

    np_acts-logits-general · gemini-2.0-flash

    adjectives often following quantifiers or negations

    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
     EconPapers
    -0.76
     Theſe
    -0.74
     schnelle
    -0.74
     poffible
    -0.71
     weißem
    -0.70
     weißen
    -0.68
     pleaſure
    -0.67
     belangrij
    -0.66
     kleinere
    -0.66
     schlechte
    -0.66
    POSITIVE LOGITS
     нее
    0.57
    참고
    0.49
    fastjson
    0.48
     bombas
    0.47
    יפה
    0.47
    FirstResponder
    0.45
     eg
    0.45
     AssemblyTitle
    0.45
     eleg
    0.45
    AccessorTable
    0.43
    Activations Density 0.037%

    No Known Activations