© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8396
    Prev
    Next
    INDEX
    Explanations

    references to governmental roles and responsibilities in the context of international cooperation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.61
     sometimes
    -0.56
     eventual
    -0.56
     even
    -0.56
    IVEREF
    -0.54
    加坡
    -0.53
    Ultimately
    -0.51
     manchmal
    -0.51
     ultimately
    -0.51
     eventually
    -0.51
    POSITIVE LOGITS
    PerformLayout
    0.76
    rungsseite
    0.73
    AndEndTag
    0.62
    Demografie
    0.61
     aforesaid
    0.60
    DoubleQuotes
    0.59
     Acting
    0.58
     Occasion
    0.57
    FailureListener
    0.56
     Chairperson
    0.55
    Activations Density 0.106%

    No Known Activations