© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 108449
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "number" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umber
    -2.33
    umbers
    -1.66
     Humber
    -1.07
    umbered
    -1.03
    ummer
    -0.91
    mber
    -0.89
    lumber
    -0.75
    umbar
    -0.73
    umb
    -0.72
    umer
    -0.62
    POSITIVE LOGITS
    XDECREF
    0.32
    kloped
    0.32
    Tính
    0.31
     disponibilités
    0.31
    ConstraintLayout
    0.30
    ficult
    0.30
     доступ
    0.29
     skrift
    0.28
    jsonwebtoken
    0.28
    JsonIgnore
    0.28
    Activations Density 0.002%

    No Known Activations