© 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. 23-GEMMASCOPE-RES-16K
    6. 14471
    Prev
    Next
    INDEX
    Explanations

    passive constructions and descriptions of processes or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.50
     jScrollPane
    -0.49
    raught
    -0.48
     egne
    -0.48
     управління
    -0.47
    丙
    -0.46
    alam
    -0.45
     logística
    -0.45
    bli
    -0.44
     reconnaît
    -0.44
    POSITIVE LOGITS
     nowadays
    0.82
    adays
    0.73
     transversal
    0.72
     somehow
    0.71
     anyhow
    0.67
    theless
    0.64
    Anyhow
    0.63
     HttpNotFound
    0.63
     transvers
    0.63
    Uhm
    0.62
    Activations Density 0.602%

    No Known Activations