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

    Neuronpedia

    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. 24-GEMMASCOPE-RES-16K
    11. 5564
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and structures related to polynomials and linear algebra

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

    Mathematical or scientific notations

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation N, r, n

    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
    indd
    -0.54
     estekak
    -0.53
    ngdoc
    -0.52
    findpost
    -0.51
    oa̍t
    -0.50
    Clik
    -0.50
    ValueMap
    -0.49
    ydd
    -0.49
    yelitis
    -0.48
    hoeddwyd
    -0.48
    POSITIVE LOGITS
    strSql
    0.36
     yourself
    0.36
    Personendaten
    0.35
     Majefty
    0.35
     sujetos
    0.35
     Peker
    0.34
     schild
    0.34
    blurRadius
    0.33
     antigüedad
    0.33
     Reglas
    0.33
    Activations Density 2.232%

    No Known Activations