© 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. 16-GEMMASCOPE-RES-16K
    11. 9351
    Prev
    Next
    INDEX
    Explanations

    instances of gratitude or acknowledgments in the text

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

    Text preceding dates or times

    np_acts-logits-general · gemini-2.0-flash

    conversational transitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⋙
    -0.81
     pinulongan
    -0.81
    ]")]
    -0.77
     CascadeType
    -0.77
     صوتيه
    -0.76
     JpaRepository
    -0.75
    Sklici
    -0.73
     snippetHide
    -0.70
    таратура
    -0.70
     мәкал
    -0.70
    POSITIVE LOGITS
     Anyway
    0.89
    Anyway
    0.83
     Anyways
    0.83
    Anyways
    0.77
     anyway
    0.71
     anyways
    0.70
    anyway
    0.68
    Anyhow
    0.68
     Sorry
    0.67
     I
    0.63
    Activations Density 0.284%

    No Known Activations