© 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. 1-GEMMASCOPE-RES-16K
    6. 6478
    Prev
    Next
    INDEX
    Explanations

    numerical values related to parameters and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ologische
    -0.57
    chymal
    -0.57
    inige
    -0.56
    踝
    -0.56
    cillor
    -0.55
    uters
    -0.54
    enic
    -0.54
    ྚ
    -0.54
    asel
    -0.54
    restler
    -0.53
    POSITIVE LOGITS
    ])))
    0.79
    ")),
    0.69
    ())),
    0.69
    ")));
    
    0.68
    )));
    
    0.68
    "]));
    0.68
    ))),
    0.67
    ])));
    0.67
    "));
    
    0.66
    })),
    0.66
    Activations Density 1.069%

    No Known Activations