© 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. 7-GEMMASCOPE-RES-16K
    6. 13858
    Prev
    Next
    INDEX
    Explanations

    instances of the conjunction "but" indicating contrast or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ″]
    -0.45
    })()
    -0.44
    //*/
    -0.43
    }}}
    
    -0.43
    ,))
    -0.43
     Doran
    -0.41
    viewmodel
    -0.41
     *)__
    -0.41
    ]=="
    -0.40
    modelName
    -0.40
    POSITIVE LOGITS
     but
    0.99
     lecz
    0.92
     tetapi
    0.81
     mutta
    0.80
     namun
    0.80
     nhưng
    0.79
     tačiau
    0.75
     pero
    0.74
     אך
    0.73
    แต่
    0.73
    Activations Density 0.256%

    No Known Activations