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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 14671
    Prev
    Next
    INDEX
    Explanations

    instances of the word "apple" and its variations in contexts related to movement or effects

    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
    suje
    -0.49
    goi
    -0.47
    msubsup
    -0.47
    RIEL
    -0.44
    NewReader
    -0.44
     Loop
    -0.43
    anillo
    -0.43
    podar
    -0.42
    śle
    -0.42
     loop
    -0.42
    POSITIVE LOGITS
     Balance
    1.08
     balance
    1.02
     équilibre
    1.00
     imbalance
    0.98
    balance
    0.97
     tipping
    0.96
    Balance
    0.94
     unbalanced
    0.93
     balances
    0.93
     Balancing
    0.92
    Activations Density 0.306%

    No Known Activations