© 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. 11356
    Prev
    Next
    INDEX
    Explanations

    programming structure and syntax elements, especially related to functions and conditionals

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

    Mentions "size"

    np_acts-logits-general · gemini-2.0-flash

    size

    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
    addCriterion
    -0.67
    routeProvider
    -0.60
    SequentialGroup
    -0.56
    fvar
    -0.53
    IVEREF
    -0.51
    หวัด
    -0.50
    didSet
    -0.49
    )|^{
    -0.49
    Referencies
    -0.49
    ALLENG
    -0.48
    POSITIVE LOGITS
     size
    3.01
    size
    2.86
     Size
    2.38
    Size
    2.34
     SIZE
    2.00
    SIZE
    1.81
     sizes
    1.80
     tamaño
    1.71
     Größe
    1.64
    サイズ
    1.56
    Activations Density 0.080%

    No Known Activations