© 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. 13710
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notation

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

    Characters and numbers within mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and sequences

    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
     xem
    -0.53
    ∑
    -0.53
    vé
    -0.52
    CppMethod
    -0.52
    pia
    -0.51
    ssis
    -0.51
    <.
    -0.51
    ilé
    -0.50
     ADDITIONAL
    -0.49
     Fore
    -0.49
    POSITIVE LOGITS
    WebVitals
    0.91
    TestBed
    0.78
     незавершена
    0.77
    MemoryWarning
    0.75
     itſelf
    0.74
     myſelf
    0.70
    ChildScrollView
    0.67
    initializeApp
    0.65
     herself
    0.62
    AnchorStyles
    0.62
    Activations Density 0.678%

    No Known Activations