© 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. 16-GEMMASCOPE-RES-16K
    11. 9230
    Prev
    Next
    INDEX
    Explanations

    average values and statistics related to various parameters

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

    Texts containing the word "average"

    np_acts-logits-general · gemini-2.0-flash

    average values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chaplin
    -0.52
     DialogInterface
    -0.51
    DrawerToggle
    -0.50
    ulemon
    -0.48
    blers
    -0.47
     most
    -0.47
     jij
    -0.46
    ksp
    -0.45
    境的
    -0.45
    Erreferentziak
    -0.45
    POSITIVE LOGITS
     AssemblyCulture
    0.88
     noDo
    0.85
     Aver
    0.85
    sidemargin
    0.77
    medio
    0.77
    存于互联网档案馆
    0.77
    LikeLike
    0.75
     AVERAGE
    0.74
    averaged
    0.74
    Personendaten
    0.73
    Activations Density 0.300%

    No Known Activations