© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1773
    Prev
    Next
    INDEX
    Explanations

    structured data in programming or coding contexts

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

    Follows a period and "Return to text."

    np_acts-logits-general · gemini-2.0-flash

    to text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -1.10
    DockStyle
    -0.95
    ⓧ
    -0.91
    SourceChecksum
    -0.91
    sizeCache
    -0.90
    matchCondition
    -0.89
     незавершена
    -0.88
     للاسماء
    -0.86
    DebuggerNonUser
    -0.85
    StructEnd
    -0.81
    POSITIVE LOGITS
     text
    3.79
    text
    3.36
     Text
    3.22
    Text
    3.10
     TEXT
    2.63
    TEXT
    2.54
     texts
    2.50
     texto
    2.26
     tekst
    2.20
     texte
    2.18
    Activations Density 0.118%

    No Known Activations