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. 3-GEMMASCOPE-RES-16K
    6. 16152
    Prev
    Next
    INDEX
    Explanations

    confirmations or statements of status regarding completion or existence, particularly in the context of actions taken

    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
    getKeyCode
    -0.60
    Билгалдахарш
    -0.59
     potes
    -0.55
    anniversaire
    -0.55
     schi
    -0.54
     erop
    -0.54
    ंगा
    -0.54
     scolaires
    -0.53
    InitVars
    -0.52
     flyg
    -0.51
    POSITIVE LOGITS
     sudah
    1.22
     Sudah
    1.16
     уже
    1.08
    Sudah
    1.07
     Уже
    1.04
    Уже
    1.03
     udah
    1.00
    已
    1.00
     már
    1.00
     вже
    0.95
    Activations Density 0.146%

    No Known Activations