© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 15767
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a significant event or situation requiring attention or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.58
    adaptiveStyles
    -0.56
    </tfoot>
    -0.54
    expandindo
    -0.49
     []:
    -0.49
    stdafx
    -0.45
     للمعارف
    -0.45
    DataPropertyName
    -0.45
    tinyos
    -0.42
    arraycopy
    -0.42
    POSITIVE LOGITS
    ativna
    0.40
     ultimi
    0.40
     betweenstory
    0.40
     laatste
    0.39
     condenado
    0.38
    ativamente
    0.38
    couverte
    0.37
     derniers
    0.37
     zaś
    0.37
    ftagPool
    0.37
    Activations Density 0.330%

    No Known Activations