© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 8593
    Prev
    Next
    INDEX
    Explanations

    instances of parentheses and discussions around beliefs or opinions regarding religious or political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ).
    -0.73
    }$.
    -0.64
    ».
    -0.63
    '.
    -0.63
    }.
    -0.63
    ’.
    -0.62
    ].
    -0.62
    ".
    -0.61
    ”.
    -0.59
     ».
    -0.58
    POSITIVE LOGITS
     autorytatywna
    1.06
     HasFactory
    0.88
    Rüyada
    0.84
    TagMode
    0.78
     estekak
    0.75
    
    0.74
    queryInterface
    0.73
    ScopeManager
    0.73
     betweenstory
    0.73
     disambiguazione
    0.72
    Activations Density 0.593%

    No Known Activations