© 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. 12-GEMMASCOPE-RES-16K
    6. 13932
    Prev
    Next
    INDEX
    Explanations

    elements related to text display and manipulation in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.52
     Roskov
    -0.50
     tartalomajánló
    -0.48
     ['$
    -0.47
    تقاوى
    -0.46
    ollectionView
    -0.44
     JADX
    -0.44
     uParam
    -0.44
    marginHorizontal
    -0.44
    flexGrow
    -0.43
    POSITIVE LOGITS
    Text
    1.86
     Text
    1.61
    setText
    1.28
     text
    1.15
    TEXT
    1.03
    text
    0.98
     TEXT
    0.96
     Texts
    0.92
     texte
    0.92
    getText
    0.92
    Activations Density 0.074%

    No Known Activations