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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 7353
    Prev
    Next
    INDEX
    Explanations

    references to "thing" in various contexts and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isticated
    -0.82
     ***/
    -0.75
     
    -0.72
    nexpected
    -0.69
    اولة
    -0.68
    letal
    -0.68
    ']]
    -0.68
     Schatten
    -0.67
     "}
    -0.67
    ."</
    -0.67
    POSITIVE LOGITS
     thing
    2.05
     THING
    1.92
     Thing
    1.84
    Thing
    1.65
    thing
    1.44
    THING
    1.42
     thingy
    1.23
     coisa
    1.13
     cosa
    0.99
     thang
    0.82
    Activations Density 0.054%

    No Known Activations