© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8572
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing exclusivity or the concept of being the sole example

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

    Follows "only" or "Only"

    np_acts-logits-general · gemini-2.0-flash

    only followed by a specific point

    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
    конец
    -0.63
     tramonto
    -0.63
    dymyr
    -0.56
    XtraEditors
    -0.53
    NewLabel
    -0.53
    stdc
    -0.52
     кӀ
    -0.50
     Meksiku
    -0.50
     fieltro
    -0.50
     بتاريخ
    -0.49
    POSITIVE LOGITS
     thing
    1.73
     reason
    1.01
     things
    0.96
     THING
    0.92
     exception
    0.87
     difference
    0.86
     downside
    0.85
     Thing
    0.82
     problem
    0.81
     caveat
    0.80
    Activations Density 0.153%

    No Known Activations