© 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. 7-GEMMASCOPE-RES-16K
    11. 4791
    Prev
    Next
    INDEX
    Explanations

    instances of the word "circle" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.86
    ########.
    -0.81
     pitié
    -0.79
    MenuInflater
    -0.78
    ˏ
    -0.76
    ntax
    -0.74
    niest
    -0.73
     fritas
    -0.72
    owulf
    -0.72
    etheless
    -0.72
    POSITIVE LOGITS
     Circle
    1.92
     circle
    1.90
     CIRCLE
    1.90
     circles
    1.87
    Circle
    1.78
     Circles
    1.73
    circle
    1.69
    Circles
    1.67
    CIRCLE
    1.60
    circles
    1.59
    Activations Density 0.089%

    No Known Activations