© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4814
    Prev
    Next
    INDEX
    Explanations

    expressions of success or effectiveness in performance

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

    "[MAX_ACTIVATING_TOKEN] well" pattern

    np_acts-logits-general · gemini-2.0-flash

    performed well

    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
     незавершена
    -0.70
     larmes
    -0.62
     assoluto
    -0.61
    Externé
    -0.60
     mauvaises
    -0.60
    ISCHE
    -0.60
    ötzlich
    -0.59
    findpost
    -0.59
    lccn
    -0.58
     متعلقه
    -0.56
    POSITIVE LOGITS
     well
    2.33
    well
    1.52
     WELL
    1.37
     excellently
    1.37
     hyvin
    1.30
     nicely
    1.30
    Well
    1.29
     better
    1.29
     Well
    1.28
     superbly
    1.24
    Activations Density 0.313%

    No Known Activations