© 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. 20-GEMMASCOPE-RES-16K
    11. 287
    Prev
    Next
    INDEX
    Explanations

    elements of code or structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     dobro
    -0.52
     vectorielles
    -0.47
     aufnehmen
    -0.47
    IENCE
    -0.45
    ucha
    -0.45
    vocato
    -0.44
     abandonné
    -0.44
    walde
    -0.44
    site
    -0.44
    енча
    -0.43
    POSITIVE LOGITS
     ExecuteAsync
    0.77
    MessageOf
    0.74
    StoreMessageInfo
    0.70
     виправивши
    0.63
     MainAxisSize
    0.62
    ItemBackground
    0.62
    MigrationBuilder
    0.62
    IndentedString
    0.60
     handleMessage
    0.59
     оригіналу
    0.59
    Activations Density 0.032%

    No Known Activations