© 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. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2243
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "numbers" and related terms in the context of statistics or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.71
     unknownFields
    -0.42
     ब्रेकडाउन
    -0.40
    engagent
    -0.39
    pretation
    -0.38
    eqref
    -0.37
    kosť
    -0.37
     duración
    -0.36
     esetben
    -0.35
    endfor
    -0.35
    POSITIVE LOGITS
     numbers
    1.79
    numbers
    1.49
     Numbers
    1.48
    Numbers
    1.48
     NUMBERS
    1.42
     Zahlen
    1.20
     chiffres
    1.14
     números
    1.10
     digits
    1.08
    Números
    0.95
    Activations Density 0.122%

    No Known Activations