© 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. 34-GEMMASCOPE-RES-16K
    11. 10892
    Prev
    Next
    INDEX
    Explanations

    terms related to the flow of electrical current and its control in various systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reactstrap
    -0.50
     onBind
    -0.49
     kasarigan
    -0.48
     оригіналу
    -0.48
    findpost
    -0.46
     <<<<<<<<<<<<<<
    -0.43
    getDoctrine
    -0.43
    蹶
    -0.41
    يكب
    -0.39
     BrowserModule
    -0.39
    POSITIVE LOGITS
     flow
    3.53
     Flow
    3.06
    flow
    2.95
    Flow
    2.91
     flows
    2.88
     FLOW
    2.77
     Flows
    2.55
     flowing
    2.47
     flowed
    2.47
    FLOW
    2.44
    Activations Density 0.739%

    No Known Activations