© 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. 7593
    Prev
    Next
    INDEX
    Explanations

    references to data collection and analysis methods in research contexts

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

    Data or information being derived or collected

    np_acts-logits-general · gemini-2.0-flash

    derived from

    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
    tagHelperRunner
    -0.81
     fermés
    -0.64
     concernés
    -0.64
     paraître
    -0.62
    tagext
    -0.61
    Autoritní
    -0.61
    reportWebVitals
    -0.60
    Vanjske
    -0.58
     Majefty
    -0.57
    AndWait
    -0.56
    POSITIVE LOGITS
     extracted
    1.58
     taken
    1.58
     obtained
    1.52
     gleaned
    1.43
     borrowed
    1.43
     drawn
    1.42
     acquired
    1.42
     sourced
    1.41
     picked
    1.39
     plucked
    1.34
    Activations Density 0.845%

    No Known Activations