© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 109627
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    HtmlAttribute
    -0.59
     HttpNotFound
    -0.47
     BoxDecoration
    -0.47
     contraire
    -0.44
     المعيارى
    -0.43
     useParams
    -0.41
     iParam
    -0.41
     InputDecoration
    -0.39
     espoir
    -0.39
     jambe
    -0.36
    POSITIVE LOGITS
    __(/*!
    0.76
    QMetaType
    0.58
    RTLD
    0.56
     CanadaChoose
    0.54
    //}
    0.52
    /**
    0.52
    }}
    0.51
    ousand
    0.50
    tiller
    0.50
    "}}
    0.50
    Activations Density 0.012%

    No Known Activations