© 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. 25-GEMMASCOPE-RES-16K
    11. 8316
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "old-fashioned" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.71
    ThroughAttribute
    -0.57
    //
    -0.54
     muualla
    -0.53
     NgModule
    -0.52
     early
    -0.51
     Wicidata
    -0.49
     currently
    -0.49
    esgue
    -0.49
    otherwise
    -0.48
    POSITIVE LOGITS
     fashioned
    1.31
    fashioned
    1.15
    school
    0.99
     skool
    0.89
     timers
    0.87
    timer
    0.83
     school
    0.82
    timers
    0.80
     adage
    0.78
     timer
    0.72
    Activations Density 0.125%

    No Known Activations