© 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. 17-GEMMASCOPE-RES-16K
    11. 13576
    Prev
    Next
    INDEX
    Explanations

    references to identity, belonging, and group dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.88
    RenderAtEndOf
    -0.82
    Autoritní
    -0.66
    DoubleQuotes
    -0.60
     jScrollPane
    -0.60
    antMatchers
    -0.58
     setia
    -0.55
    følgelig
    -0.54
    IUrlHelper
    -0.53
    ณา
    -0.52
    POSITIVE LOGITS
     unfamiliar
    1.27
     strangers
    1.19
     unrelated
    1.16
     stranger
    0.99
     desconoc
    0.94
     distant
    0.94
     unknown
    0.92
    陌
    0.90
     desconhe
    0.88
     fremden
    0.87
    Activations Density 0.561%

    No Known Activations