© 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. 40-GEMMASCOPE-RES-16K
    11. 5187
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of pipes and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addWidget
    -0.40
     propOrder
    -0.38
     SwitchCompat
    -0.38
    NullCheck
    -0.37
    ⤹
    -0.36
    VYMaps
    -0.35
    IndentedString
    -0.35
    Портал
    -0.35
    ModelForm
    -0.35
    astify
    -0.34
    POSITIVE LOGITS
     pipe
    1.82
     pipes
    1.65
     Pipe
    1.57
     pipeline
    1.53
    pipe
    1.50
    Pipe
    1.49
     pipelines
    1.45
     Pipes
    1.39
     piping
    1.34
     Pipeline
    1.33
    Activations Density 0.374%

    No Known Activations