© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7329
    Prev
    Next
    INDEX
    Explanations

    references to "mat" or its variations in the context of materials or formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doInBackground
    -0.47
    HomeAsUpEnabled
    -0.43
     autorytatywna
    -0.42
    klart
    -0.36
    ☚
    -0.36
    Ừ
    -0.35
    VYMaps
    -0.35
    Aktualisiert
    -0.35
    oğlu
    -0.34
    tinya
    -0.33
    POSITIVE LOGITS
     MAT
    1.19
     mat
    1.19
    MAT
    1.14
    Mat
    1.11
     Mat
    1.06
    mat
    1.02
    mats
    0.93
     mats
    0.90
     Lamb
    0.90
     Mathews
    0.88
    Activations Density 1.677%

    No Known Activations