© 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. 12-GEMMASCOPE-RES-16K
    11. 15040
    Prev
    Next
    INDEX
    Explanations

    references to companies and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HttpNotFound
    -0.99
     Theſe
    -0.84
     autorytatywna
    -0.82
    ftagPool
    -0.81
    WireFormatLite
    -0.74
    mybatisplus
    -0.72
     kasarigan
    -0.72
     تجمعات
    -0.71
    AndEndTag
    -0.71
     avoient
    -0.69
    POSITIVE LOGITS
     Professional
    0.55
     professional
    0.51
     specializing
    0.51
     professionals
    0.47
     specializes
    0.47
     A
    0.46
    Professional
    0.46
     B
    0.46
     Services
    0.46
     S
    0.46
    Activations Density 0.165%

    No Known Activations