© 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. 24-GEMMASCOPE-RES-16K
    6. 12105
    Prev
    Next
    INDEX
    Explanations

    elements that highlight themes of absurdity and social commentary in film

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

    Follows "the", "their", "its" or "a"

    np_acts-logits-general · gemini-2.0-flash

    the own story easiest sexual promising latest favorite

    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
     poichè
    -1.05
     Whilst
    -1.01
    Whilst
    -0.98
    "..
    -0.91
     pò
    -0.89
     diatas
    -0.87
     dibawah
    -0.85
     jepang
    -0.85
     betek
    -0.84
     whilst
    -0.83
    POSITIVE LOGITS
     freilich
    0.86
     cheerfully
    0.86
     eminently
    0.83
    eabouts
    0.80
     lousy
    0.77
    けっこう
    0.73
     inexorable
    0.73
     putative
    0.73
     weirdly
    0.72
     interminable
    0.72
    Activations Density 0.828%

    No Known Activations