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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 699
    Prev
    Next
    INDEX
    Explanations

    punctuation and the mathematical or logical structure in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     avoient
    -0.87
     miniaturka
    -0.78
     feroit
    -0.77
     zijne
    -0.74
    principalColumn
    -0.73
     étoient
    -0.71
     pescoço
    -0.70
     titolata
    -0.70
     auroit
    -0.68
     ainfi
    -0.67
    POSITIVE LOGITS
    -->
    
    0.54
    ()));
    
    0.52
    })}
    0.52
     Dak
    0.50
    }
    
    
    0.50
    )));
    
    0.50
    )";
    
    0.49
    ]')
    0.49
    ۜ
    0.49
    )));
    0.49
    Activations Density 1.049%

    No Known Activations