© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 16220
    Prev
    Next
    INDEX
    Explanations

    references to "side" 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 @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Erfurt
    -0.84
    transQ
    -0.83
     poveznice
    -0.82
    новниш
    -0.82
     betweenstory
    -0.81
    ']);
    
    -0.80
    jillo
    -0.80
    ]));
    
    -0.79
    PerformLayout
    -0.78
    $).
    -0.77
    POSITIVE LOGITS
     side
    2.73
     Side
    2.59
     SIDE
    2.54
    Side
    2.49
     sides
    2.38
    side
    2.29
    SIDE
    2.20
     Sides
    2.11
    sides
    1.82
    Sides
    1.82
    Activations Density 0.058%

    No Known Activations