© 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. 7635
    Prev
    Next
    INDEX
    Explanations

    technical terms associated with anatomical and physiological studies

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

    preceding measurements or calculations

    np_acts-logits-general · gemini-2.0-flash

    determining location and rate

    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
     Nowadays
    -1.25
    Nowadays
    -1.19
     nowadays
    -1.08
     programmes
    -0.98
     programme
    -0.94
     marvellous
    -0.94
    Ещё
    -0.93
     specialises
    -0.92
    defence
    -0.91
     Programmes
    -0.91
    POSITIVE LOGITS
     hypothesized
    0.85
     geologic
    0.69
     utilizing
    0.68
     Percent
    0.67
     nominally
    0.66
    ologic
    0.66
     modeled
    0.65
     disparate
    0.65
     physiologic
    0.64
     foundational
    0.64
    Activations Density 2.660%

    No Known Activations