© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 2182
    Prev
    Next
    INDEX
    Explanations

    instances of excessive or inappropriate behavior, particularly in the context of measurements or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.67
     snippetHide
    -0.67
    })));
    -0.56
    anthes
    -0.54
    \{\
    -0.54
    
    -0.54
    templateUrl
    -0.53
     lustig
    -0.53
    usec
    -0.52
    autoreleasepool
    -0.52
    POSITIVE LOGITS
     Too
    0.84
    Too
    0.82
     exces
    0.81
     Overs
    0.80
     Excessive
    0.78
     excessive
    0.77
    Excessive
    0.75
     overs
    0.74
     exceso
    0.73
    دانشنامهٔ
    0.72
    Activations Density 0.265%

    No Known Activations