© 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. 1-GEMMASCOPE-RES-16K
    11. 5834
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pri."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -0.92
     LXXX
    -0.85
     Efq
    -0.82
     itſelf
    -0.80
     myſelf
    -0.77
     ſtate
    -0.77
     iſt
    -0.76
     Majefty
    -0.73
     **/
    -0.73
     purpoſe
    -0.71
    POSITIVE LOGITS
     при
    3.68
    При
    2.93
     При
    2.79
    при
    2.59
     przy
    2.52
     ПРИ
    2.38
    Przy
    1.89
     při
    1.82
    ПРИ
    1.79
    przy
    1.79
    Activations Density 0.047%

    No Known Activations