© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 41-GEMMASCOPE-RES-16K
    11. 11026
    Prev
    Next
    INDEX
    Explanations

    code snippets and related programming syntax

    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
     RR
    -1.38
     RP
    -1.27
     RE
    -1.27
     RL
    -1.27
     RC
    -1.25
     RB
    -1.24
     RH
    -1.24
     RS
    -1.23
     RK
    -1.22
     Rc
    -1.22
    POSITIVE LOGITS
    AndEndTag
    0.24
    GTCX
    0.24
    ioneta
    0.23
    cantara
    0.23
    migrationBuilder
    0.23
    ACIO
    0.23
    Бахар
    0.23
    IPMENT
    0.22
    岱
    0.22
    OptionPane
    0.22
    Activations Density 3.531%

    No Known Activations