© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6620
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of withdrawing or withholding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.66
     onOptions
    -0.65
    ContentAsync
    -0.63
     ExecuteAsync
    -0.60
     getItemId
    -0.58
    Välislingid
    -0.55
    bcryptjs
    -0.54
    >--}}
    -0.54
    umerable
    -0.54
    cap
    -0.53
    POSITIVE LOGITS
     withdraws
    1.56
     withdraw
    1.52
     Withdraw
    1.49
     withdrawal
    1.45
     withdrawn
    1.44
     withdrawing
    1.42
     withdrew
    1.40
     withhold
    1.35
     withdrawals
    1.33
     withheld
    1.32
    Activations Density 0.269%

    No Known Activations