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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5107
    Prev
    Next
    INDEX
    Explanations

    references to financial costs and investments associated with projects or developments

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

    Text occurring after the tokens "a", "0", or "m"

    np_acts-logits-general · gemini-2.0-flash

    creative lifestyle and calculation

    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
     Seguridad
    -0.49
     raisonnable
    -0.48
     ancianos
    -0.48
     médicale
    -0.47
     catholique
    -0.46
     nucléaire
    -0.45
     católica
    -0.45
     Turquía
    -0.45
     médical
    -0.43
     povin
    -0.42
    POSITIVE LOGITS
     hipster
    0.95
     cowork
    0.68
     loft
    0.68
     noDo
    0.66
     bohemian
    0.65
     creatives
    0.65
     brunch
    0.64
    ngdoc
    0.63
     creative
    0.63
     XO
    0.63
    Activations Density 0.219%

    No Known Activations