© 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. 3064
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables related to integrals and intervals

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

    "in [0, T]" or "in I"

    np_acts-logits-general · gemini-2.0-flash

    "in" followed by interval notation

    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
     kaarangay
    -0.53
    ējās
    -0.52
     HttpNotFound
    -0.48
    offsetof
    -0.48
    VENT
    -0.45
    cima
    -0.44
    Await
    -0.44
    zahl
    -0.43
    size
    -0.43
    ีม
    -0.43
    POSITIVE LOGITS
     interval
    1.18
     Interval
    1.08
    Interval
    1.03
    interval
    0.96
     intervals
    0.94
     INTERVAL
    0.93
     [-
    0.87
     $[-
    0.86
     Intervals
    0.86
    INTERVAL
    0.82
    Activations Density 0.913%

    No Known Activations