© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 44567
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams and associated events in a specific geographical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Newcastle region viruses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.53
    IntoConstraints
    -0.51
    ulemon
    -0.46
    ]")]
    -0.44
     veranderen
    -0.44
    jspb
    -0.44
    PostInfinity
    -0.43
    úrese
    -0.43
    SharedDtor
    -0.42
    ⎠
    -0.41
    POSITIVE LOGITS
     Newcastle
    1.23
    Newcastle
    1.15
     Northumberland
    1.05
     Tyne
    0.88
     Durham
    0.81
     Geor
    0.78
    Durham
    0.71
     Sunderland
    0.64
     Toon
    0.63
    Geor
    0.59
    Activations Density 0.030%

    No Known Activations