© 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. 6101
    Prev
    Next
    INDEX
    Explanations

    questions related to existence, significance, and interpretation of concepts

    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
     ?',
    -0.39
    parsedMessage
    -0.37
    usercontent
    -0.36
     sumpay
    -0.36
    fastjson
    -0.36
     ?";
    -0.36
    CLUS
    -0.35
    umina
    -0.35
    StandardCharsets
    -0.34
     Mul
    -0.34
    POSITIVE LOGITS
     للمعارف
    0.58
    AndEndTag
    0.57
     nahilalakip
    0.50
    complexContent
    0.49
     sério
    0.47
     <<<<<<<<<<<<<<
    0.45
     ActionListener
    0.44
     seduta
    0.43
     Valky
    0.42
     óptica
    0.42
    Activations Density 0.388%

    No Known Activations