© 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. 41-GEMMASCOPE-RES-16K
    6. 8050
    Prev
    Next
    INDEX
    Explanations

    phrases indicating location or reference to spatial relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.44
    ReusableCell
    -0.43
    NameInMap
    -0.39
    WAUKEE
    -0.39
    fromnode
    -0.38
    +#+#
    -0.38
    QRST
    -0.37
     Савезне
    -0.37
    ēju
    -0.36
    ValueGenerated
    -0.36
    POSITIVE LOGITS
     Moment
    0.44
     referrerpolicy
    0.42
     momentos
    0.41
    Moments
    0.40
     timp
    0.40
    moments
    0.39
     momento
    0.39
     offseason
    0.38
     Extrem
    0.38
    Moment
    0.38
    Activations Density 0.064%

    No Known Activations