© 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. 22-GEMMASCOPE-RES-16K
    11. 11722
    Prev
    Next
    INDEX
    Explanations

    terms related to classification and taxonomic structures

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

    Inconsistencies and confusing terminology

    np_acts-logits-general · gemini-2.0-flash

    clarifying inconsistent terminology

    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
    parsedMessage
    -0.94
    RectangleBorder
    -0.84
     AssemblyTitle
    -0.65
    ThroughAttribute
    -0.60
    InjectAttribute
    -0.59
     ProtoMessage
    -0.58
    ChildScrollView
    -0.57
    TargetException
    -0.56
    jublj
    -0.56
    ätzt
    -0.55
    POSITIVE LOGITS
     confusing
    0.99
     confusion
    0.98
     convention
    0.92
     consistent
    0.90
     conventions
    0.89
     inconsistent
    0.89
    Confusion
    0.89
    consistency
    0.86
     consistency
    0.86
    consistent
    0.85
    Activations Density 0.653%

    No Known Activations