Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10520
    Prev
    Next
    INDEX
    Explanations

    names of educational institutions and their locations

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

    Follows preposition "in" or delimiters "," and "-"

    np_acts-logits-general · gemini-2.0-flash

    Long Island or place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -1.07
    Personendaten
    -0.79
    AccessorTable
    -0.79
     @"/
    -0.69
     nakalista
    -0.68
     Olimpia
    -0.68
    $_['
    -0.65
     "..\..\
    -0.64
    MarshalTo
    -0.64
    IUrlHelper
    -0.63
    POSITIVE LOGITS
     Long
    1.47
    Long
    1.24
     LONG
    0.96
    LONG
    0.94
    long
    0.80
     long
    0.79
     LI
    0.71
     Nassau
    0.70
     Hof
    0.70
     Farming
    0.69
    Activations Density 0.146%

    No Known Activations