© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104422
    Prev
    Next
    INDEX
    Explanations

    functions and structures associated with system messages and data handling in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -0.39
    }}],
    -0.39
     an
    -0.38
    }]);
    -0.36
     F
    -0.35
     x
    -0.34
     f
    -0.34
     v
    -0.34
     un
    -0.34
    }});
    -0.34
    POSITIVE LOGITS
     HasFactory
    0.74
     GenerationType
    0.72
     Paglinawan
    0.68
    +#+#
    0.68
    ########.
    0.67
    linawan
    0.66
    centralwidget
    0.66
    Personensuche
    0.66
     himſelf
    0.64
    elemField
    0.63
    Activations Density 0.013%

    No Known Activations