Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16235
    Prev
    Next
    INDEX
    Explanations

    numeric values and scientific notation in the context of physics or experimental data

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

    Numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and numerical data

    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
    ⓧ
    -1.17
    SequentialGroup
    -0.83
    CloseOperation
    -0.75
    verwijspagina
    -0.70
     CURIAM
    -0.67
    tagHelperRunner
    -0.63
     שוליים
    -0.60
     مشين
    -0.58
     oprot
    -0.57
     Wikispecies
    -0.56
    POSITIVE LOGITS
    1
    1.53
    2
    1.52
    3
    1.47
    5
    1.47
    6
    1.42
    4
    1.40
    9
    1.39
    7
    1.37
    8
    1.35
    0
    1.31
    Activations Density 2.346%

    No Known Activations