© 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1866
    Prev
    Next
    INDEX
    Explanations

    technical terms and adjustments related to photography

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

    setting maximums or ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.69
    enumii
    -0.59
     prezzi
    -0.57
    KommentareTeilen
    -0.56
    ValueStyle
    -0.55
     împre
    -0.53
     proprement
    -0.53
     sobrevi
    -0.52
     esistono
    -0.52
     blandt
    -0.51
    POSITIVE LOGITS
     settings
    0.93
     max
    0.83
     Settings
    0.82
     maximum
    0.78
     setting
    0.76
     maxed
    0.74
     SETTINGS
    0.73
    settings
    0.73
    Settings
    0.69
     full
    0.67
    Activations Density 0.086%

    No Known Activations