© 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. 7-GEMMASCOPE-RES-16K
    11. 10226
    Prev
    Next
    INDEX
    Explanations

    patterns related to concatenation or string manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.56
     invece
    -0.54
    енча
    -0.52
     concent
    -0.50
    =[]
    -0.50
     Ch
    -0.50
    bellar
    -0.50
     ch
    -0.49
     CH
    -0.49
    وردار
    -0.48
    POSITIVE LOGITS
     nahilalakip
    1.08
    帖最后由
    1.04
    __*/
    1.02
    ">'+
    0.97
    日閲覧
    0.93
    MigrationBuilder
    0.92
    escaping
    0.92
    økt
    0.90
    migrationBuilder
    0.87
    URLException
    0.85
    Activations Density 0.016%

    No Known Activations