© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14573
    Prev
    Next
    INDEX
    Explanations

    structured data and patterns related to variables and conditions

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

    Numbers followed by a right parenthesis

    np_acts-logits-general · gemini-2.0-flash

    numbers ending in ten

    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
     تانيه
    -0.57
    ništ
    -0.52
    |}{}
    -0.52
     समीक्षाओं
    -0.51
     Yang
    -0.51
    alz
    -0.49
    ICLES
    -0.48
    джер
    -0.48
    ANGES
    -0.48
    irer
    -0.47
    POSITIVE LOGITS
     ten
    1.33
     Ten
    1.33
    Ten
    1.30
     Tenth
    1.22
     tenth
    1.18
     TEN
    1.15
    ten
    1.03
     dieci
    0.98
    tenth
    0.96
    TEN
    0.95
    Activations Density 0.322%

    No Known Activations