© 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-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8413
    Prev
    Next
    INDEX
    Explanations

    references to communication channels in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    ])));
    -0.56
    ]){
    
    -0.54
     *
    
    
    -0.51
    "])
    
    -0.51
    '])
    
    -0.51
    "]);
    
    -0.50
    }))
    
    -0.49
    ')))
    -0.49
     }</
    -0.48
    })`
    -0.48
    POSITIVE LOGITS
     channel
    1.63
    Channel
    1.56
    channel
    1.54
     Channel
    1.48
     channels
    1.47
     Channels
    1.42
     CHANNEL
    1.40
    channels
    1.39
    Channels
    1.38
    CHANNEL
    1.31
    Activations Density 0.048%

    No Known Activations