© 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. 7-GEMMASCOPE-RES-16K
    11. 15417
    Prev
    Next
    INDEX
    Explanations

    instances of the word "break" and its variations, especially in relation to processes or systems that fail or deteriorate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.47
    JKLM
    -0.44
     propOrder
    -0.43
     հղումներ
    -0.41
    ClientSize
    -0.40
    tangentMode
    -0.40
     שוליים
    -0.40
    Turtle
    -0.40
    MemoryWarning
    -0.40
    ContentAlignment
    -0.39
    POSITIVE LOGITS
     breakdown
    1.74
     Breakdown
    1.59
    Breakdown
    1.54
     breakdowns
    1.45
    breakdown
    1.34
     decomposition
    1.26
    分解
    1.16
     decompose
    1.13
     Decomposition
    1.12
    decomposition
    1.04
    Activations Density 0.283%

    No Known Activations