© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2274
    Prev
    Next
    INDEX
    Explanations

    sections that describe methodologies or theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Starts with "We," "Let," or variations

    np_acts-logits-general · gemini-2.0-flash

    introductions or descriptions using "we" or "let"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.78
     Signalez
    -0.66
     Administrativna
    -0.59
     الرياضيه
    -0.58
     Vikipedi
    -0.56
    queryInterface
    -0.55
    oa̍t
    -0.52
     AssemblyTitle
    -0.52
    MemoryWarning
    -0.52
    Chham
    -0.52
    POSITIVE LOGITS
     We
    0.41
     Let
    0.41
     let
    0.39
     we
    0.37
     bid
    0.36
    Let
    0.35
     modelling
    0.35
     assume
    0.34
    Tracce
    0.34
    We
    0.34
    Activations Density 1.669%

    No Known Activations