© 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. 20-GEMMASCOPE-RES-16K
    11. 1201
    Prev
    Next
    INDEX
    Explanations

    technical terms and structures related to programming or database schema definitions

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

    Code, programming, and software-related strings

    np_acts-logits-general · gemini-2.0-flash

    din dinucleotide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rhestr
    -0.74
    GraphicsUnit
    -0.63
    #+#
    -0.60
    +#+#
    -0.57
    ponses
    -0.57
    sidemargin
    -0.56
    تقاوى
    -0.54
    Condol
    -0.54
     estekak
    -0.53
    sizePolicy
    -0.53
    POSITIVE LOGITS
     endforeach
    0.51
     IBOutlet
    0.50
    AccessorTable
    0.49
     string
    0.48
     Poli
    0.46
     binary
    0.46
    UnusedPrivate
    0.45
    ++
    0.44
     Mord
    0.43
     text
    0.43
    Activations Density 0.076%

    No Known Activations