© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11996
    Prev
    Next
    INDEX
    Explanations

    references to materials and their specific properties or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NUMX
    -0.87
    ')")
    -0.86
     محفوظة
    -0.83
    }\]
    -0.78
    __))
    -0.77
    }")
    
    -0.76
     betweenstory
    -0.75
    ")));
    
    -0.75
    }]);
    -0.73
    存于互联网档案馆
    -0.72
    POSITIVE LOGITS
    –
    1.55
    /
    1.38
    -
    1.11
    /
    1.01
    −
    1.00
     /
    0.97
    ->
    0.94
    ・
    0.92
    ‒
    0.86
    -
    0.86
    Activations Density 1.202%

    No Known Activations