© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 2736
    Prev
    Next
    INDEX
    Explanations

    structure or syntax in programming or code-related contexts

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

    before categories

    np_acts-logits-general · gemini-2.0-flash

    Category or reference identifiers

    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
     STD
    -0.63
    middels
    -0.56
    migrationBuilder
    -0.56
     Stonehenge
    -0.55
    BrowserModule
    -0.53
     jewellery
    -0.52
    prepareStatement
    -0.51
     precedence
    -0.50
     NBS
    -0.50
     barbie
    -0.49
    POSITIVE LOGITS
    BuildContext
    0.68
     通販
    0.58
    Datuak
    0.57
     لينك
    0.54
    required
    0.52
     dynamic
    0.52
    aternary
    0.49
    achery
    0.49
    álny
    0.48
     double
    0.48
    Activations Density 0.104%

    No Known Activations