© 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. 2-GEMMASCOPE-RES-16K
    11. 3501
    Prev
    Next
    INDEX
    Explanations

    instances of the word "properly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addCriterion
    -0.65
     виправивши
    -0.58
    ǔ
    -0.57
     <<<<<<<<<<<<<<
    -0.57
     Leger
    -0.56
    belec
    -0.55
    VideoCapture
    -0.55
     dépos
    -0.55
    RTGC
    -0.54
    loé
    -0.54
    POSITIVE LOGITS
     correctly
    2.33
     properly
    2.29
    properly
    1.96
     Properly
    1.96
    correctly
    1.79
     correctement
    1.57
     appropriately
    1.49
     correctamente
    1.46
     accurately
    1.33
     corretamente
    1.32
    Activations Density 0.119%

    No Known Activations