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

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    6. 9101
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical models and their assumptions

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

    Word(s) preceding "properties," "property," or "requirement"

    np_acts-logits-general · gemini-2.0-flash

    satisfying properties or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.64
    Carriera
    -0.61
    DataSnapshot
    -0.58
    JspWriter
    -0.58
    MLLoader
    -0.57
    CodeAttribute
    -0.55
    RunWith
    -0.55
     himo
    -0.54
    RTEE
    -0.54
    BeginContext
    -0.53
    POSITIVE LOGITS
     property
    0.92
     properties
    0.88
     Property
    0.78
    property
    0.76
     conservation
    0.74
    Property
    0.73
     Properties
    0.71
    properties
    0.69
     station
    0.68
     requirement
    0.67
    Activations Density 1.740%

    No Known Activations