© 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. 19-GEMMASCOPE-RES-16K
    11. 602
    Prev
    Next
    INDEX
    Explanations

    phrases related to occurrences of being in the wrong place and time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ويكيميديا
    -0.57
    CIÓN
    -0.51
    цездатний
    -0.49
    WebControls
    -0.49
    収録曲
    -0.48
     Weekend
    -0.48
    GraphicsUnit
    -0.46
     ModelAndView
    -0.46
    dozen
    -0.45
     виправивши
    -0.44
    POSITIVE LOGITS
     time
    2.16
     Time
    1.77
    time
    1.77
    Time
    1.74
     TIME
    1.65
     temporal
    1.52
    时间
    1.50
     시간
    1.49
    TIME
    1.49
     tijd
    1.45
    Activations Density 1.096%

    No Known Activations