© 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. 12-GEMMASCOPE-RES-16K
    11. 11598
    Prev
    Next
    INDEX
    Explanations

    references to memory addresses or address indicators in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )();
    -0.57
     gap
    -0.57
    ('');
    -0.56
    ...]
    -0.56
    ='')
    -0.56
     ());
    -0.55
    …)
    -0.54
     fal
    -0.54
    '))
    -0.54
    '])
    -0.54
    POSITIVE LOGITS
    enumi
    1.03
     &___
    0.98
     feroit
    0.96
    (&
    0.94
    InjectAttribute
    0.92
     étoient
    0.91
     avoient
    0.91
    ValueStyle
    0.88
     auroit
    0.85
     trouvera
    0.85
    Activations Density 0.058%

    No Known Activations