© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15711
    Prev
    Next
    INDEX
    Explanations

    references to corporate communication elements and contact information

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

    contact information and press release formatting elements like names, email addresses, phone numbers, and institutional headers.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    PathVariable
    -0.40
     tatuagem
    -0.34
    nungszeiten
    -0.32
    patrón
    -0.32
    ViewFeatures
    -0.32
     almofada
    -0.30
    ñor
    -0.30
     AssemblyTitle
    -0.30
     tartış
    -0.30
    árbol
    -0.30
    POSITIVE LOGITS
     press
    1.86
     Press
    1.59
    Press
    1.54
    press
    1.52
     PR
    1.52
     PRESS
    1.45
     Presse
    1.38
     пресс
    1.36
     presse
    1.36
    プレス
    1.30
    Activations Density 0.193%

    No Known Activations