© 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. 16-GEMMASCOPE-RES-16K
    11. 7081
    Prev
    Next
    INDEX
    Explanations

    the start of a new document or section

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

    Follows a capital letter

    np_acts-logits-general · gemini-2.0-flash

    specific items after "after"

    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
    EndGlobalSection
    -1.14
    SharedDtor
    -1.05
    yntaxException
    -1.04
    complexContent
    -1.03
     CreateTagHelper
    -1.02
    ValueStyle
    -0.98
     تانيه
    -0.98
    AccessorTable
    -0.95
    fjspx
    -0.94
     '\\;'
    -0.94
    POSITIVE LOGITS
    <eos>
    0.72
    B
    0.63
    A
    0.54
    L
    0.52
    K
    0.49
    C
    0.48
    I
    0.48
    G
    0.48
    P
    0.47
    R
    0.46
    Activations Density 0.032%

    No Known Activations