© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11650
    Prev
    Next
    INDEX
    Explanations

    instances of the word "finally."

    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
     specchio
    -0.67
     sklad
    -0.61
     piele
    -0.58
     znam
    -0.58
     uč
    -0.58
     Ruhr
    -0.57
     Saks
    -0.57
     Cock
    -0.56
     vertes
    -0.55
    pera
    -0.55
    POSITIVE LOGITS
     finally
    3.21
    finally
    3.04
     Finally
    2.82
    Finally
    2.69
     FINALLY
    2.62
     finalmente
    2.50
     Finalmente
    2.31
    Finalmente
    2.28
     enfin
    2.27
    FINALLY
    2.22
    Activations Density 0.045%

    No Known Activations