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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10664
    Prev
    Next
    INDEX
    Explanations

    expressions of congratulations and well-wishing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.58
    autoIncrement
    -0.51
    scape
    -0.50
     convaincre
    -0.49
    存于互联网档案馆
    -0.49
     Rest
    -0.48
     schlafen
    -0.48
    mott
    -0.48
    InStock
    -0.47
    chown
    -0.47
    POSITIVE LOGITS
     greetings
    1.28
     congratulations
    1.25
     congrat
    1.25
     congratulate
    1.17
     congratulated
    1.10
     wishes
    1.10
     condolences
    1.08
     greeting
    1.04
     wishing
    1.03
     condolence
    0.99
    Activations Density 0.152%

    No Known Activations