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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11491
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "giving up."

    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
     Auft
    -0.54
    BLO
    -0.54
     diffus
    -0.52
     Nightingale
    -0.51
     COA
    -0.48
     tabi
    -0.48
     Hatt
    -0.47
    対応
    -0.47
    mathscr
    -0.47
     Minaj
    -0.46
    POSITIVE LOGITS
     abandonment
    1.56
     Abandon
    1.53
     abandon
    1.50
    Abandon
    1.49
    abandon
    1.42
     abandoning
    1.41
     abandoned
    1.34
     abandonné
    1.34
     abbandon
    1.29
     Abandoned
    1.27
    Activations Density 0.167%

    No Known Activations