© 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. 16-GEMMASCOPE-RES-16K
    6. 3257
    Prev
    Next
    INDEX
    Explanations

    references to environmental and health-related topics

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

    followed by prepositions or "are"

    np_acts-logits-general · gemini-2.0-flash

    types of things usually

    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
    DockStyle
    -0.77
    extAlignment
    -0.64
     Lightboxes
    -0.62
    +#+#
    -0.56
    onViewCreated
    -0.54
     typelib
    -0.54
     তারিখ
    -0.54
    jacency
    -0.53
    دانشنامهٔ
    -0.52
     vors
    -0.51
    POSITIVE LOGITS
     usually
    0.86
     typically
    0.79
     often
    0.77
     biasanya
    0.77
     normally
    0.72
    usually
    0.71
    Usually
    0.70
     genellikle
    0.70
     geralmente
    0.69
     zwykle
    0.68
    Activations Density 1.063%

    No Known Activations