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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2197
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a sense of culmination or realization

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

    "Finally" or words with similar meanings

    np_acts-logits-general · gemini-2.0-flash

    arrival at completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]-->
    -0.55
     متعلقه
    -0.53
     '../
    -0.45
    "?>
    -0.45
     "../
    -0.44
    dien
    -0.43
    ご了承ください
    -0.43
    出版年
    -0.43
    ']):
    -0.43
     alatt
    -0.43
    POSITIVE LOGITS
     finally
    3.27
    finally
    3.06
     Finally
    2.71
    Finally
    2.68
     FINALLY
    2.67
     enfin
    2.65
     finalmente
    2.60
     наконец
    2.54
     endlich
    2.42
    FINALLY
    2.35
    Activations Density 0.383%

    No Known Activations