© 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. 11291
    Prev
    Next
    INDEX
    Explanations

    numerical values and sequences commonly found in technical or scientific contexts

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

    Bytes/numbers followed by brackets

    np_acts-logits-general · gemini-2.0-flash

    micro liters

    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
    
    -0.63
    rungsseite
    -0.50
     ModelExpression
    -0.47
    IntoConstraints
    -0.47
    AISSEE
    -0.45
    :+:
    -0.44
     <<<<<<<<<<<<<<
    -0.43
    ConstraintMaker
    -0.42
    AtIndexPath
    -0.41
    GetKeyDown
    -0.41
    POSITIVE LOGITS
     larger
    0.75
    larger
    0.68
     Larger
    0.63
    Larger
    0.63
     bigger
    0.60
     majority
    0.59
     hundreds
    0.54
     bulk
    0.53
     Vast
    0.53
     vast
    0.53
    Activations Density 1.057%

    No Known Activations