© 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. 2620
    Prev
    Next
    INDEX
    Explanations

    instances of the substring "ak" or similar variations in names

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

    ending in "k"

    np_acts-logits-general · gemini-2.0-flash

    ik, ak, mk beginnings

    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
     newOwner
    -0.76
    awtextra
    -0.70
    ISupport
    -0.68
     فريبيس
    -0.67
    RectangleBorder
    -0.65
    Traceback
    -0.62
    subpackage
    -0.61
    DockStyle
    -0.61
    NameInMap
    -0.60
    ValueStyle
    -0.60
    POSITIVE LOGITS
    night
    0.56
    inetic
    0.54
    nights
    0.53
     fermés
    0.52
    iewicz
    0.50
     sauvages
    0.50
    owski
    0.48
    em
    0.48
     particulières
    0.47
     noires
    0.47
    Activations Density 0.216%

    No Known Activations