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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 50636
    Prev
    Next
    INDEX
    Explanations

    the word 'finally' and its variations, indicating a sense of resolution or culmination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    finally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     theme
    -0.39
     basket
    -0.38
     pé
    -0.38
     beverages
    -0.38
     colleg
    -0.37
     Vors
    -0.37
    OrWhiteSpace
    -0.36
     Hoop
    -0.36
     items
    -0.36
     Web
    -0.36
    POSITIVE LOGITS
     finally
    1.53
    finally
    1.34
     finalmente
    1.29
     FINALLY
    1.27
     endlich
    1.15
     enfin
    1.10
     Finally
    1.10
     Finalmente
    1.08
    Finally
    1.07
     Endlich
    1.06
    Activations Density 0.008%

    No Known Activations