© 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. 8662
    Prev
    Next
    INDEX
    Explanations

    specific brand names and product identifiers

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

    that start with specific letters

    np_acts-logits-general · gemini-2.0-flash

    proper nouns that start specific phrases

    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
    ↵
    -0.30
    ↵↵
    -0.28
     last
    -0.25
     rather
    -0.24
     (
    -0.23
      
    -0.23
     from
    -0.22
     known
    -0.22
     long
    -0.22
     fine
    -0.22
    POSITIVE LOGITS
    rungsseite
    0.99
    parsedMessage
    0.98
    ſammen
    0.90
     MainAxisSize
    0.90
    niſſe
    0.88
     resourceCulture
    0.86
     Geiſt
    0.85
     Италијани
    0.84
     noDo
    0.83
    ſelben
    0.82
    Activations Density 1.871%

    No Known Activations