© 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. 22-GEMMASCOPE-RES-16K
    6. 3136
    Prev
    Next
    INDEX
    Explanations

    closing braces and function return statements, indicating the end of code blocks or functions

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

    Code snippets or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    finally / eventually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.88
     elif
    -0.87
    TagMode
    -0.74
     ELSE
    -0.72
    elif
    -0.71
     OTHER
    -0.70
    stdafx
    -0.69
     OTHERS
    -0.68
     AppColors
    -0.68
     Monfieur
    -0.67
    POSITIVE LOGITS
     finally
    1.56
    finally
    1.45
     Finally
    1.19
    Finally
    1.18
     finalmente
    1.03
     eventually
    0.98
     akhirnya
    0.93
     enfin
    0.91
     FINALLY
    0.90
     finalement
    0.87
    Activations Density 0.038%

    No Known Activations