© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15244
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and structures relevant to equations and expressions

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

    Mathematical or numerical expressions

    np_acts-logits-general · gemini-2.0-flash

    indices `i`, `j`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.74
     חיצוניים
    -0.68
     intptr
    -0.65
     defaultstate
    -0.65
    Autoritní
    -0.64
     doInBackground
    -0.63
     ſei
    -0.61
    __':
    -0.60
    __':
    -0.59
     utafitiHapana
    -0.59
    POSITIVE LOGITS
     morgon
    0.34
    ậy
    0.33
    rceil
    0.32
     gouttes
    0.31
    enterOuterAlt
    0.30
    StoryboardSegue
    0.30
    Buildable
    0.30
     högre
    0.28
     höher
    0.28
    越高
    0.28
    Activations Density 0.700%

    No Known Activations