© 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. 1853
    Prev
    Next
    INDEX
    Explanations

    sentences that express potential benefits or positive outcomes

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

    Advantages, blessings, and good things

    np_acts-logits-general · gemini-2.0-flash

    advantage and disadvantage

    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
    verwijspagina
    -0.42
    anyan
    -0.40
    InternalFrame
    -0.40
     exp
    -0.39
     Schützen
    -0.38
    tren
    -0.38
     кӀ
    -0.38
    UIApplication
    -0.36
     disambiguazione
    -0.36
     Witherspoon
    -0.36
    POSITIVE LOGITS
    SequentialGroup
    0.71
     advantageous
    0.52
     vantaggio
    0.51
     disadvantages
    0.50
     disadvantage
    0.49
     odkazy
    0.48
    styleType
    0.48
     ModelExpression
    0.48
    featureID
    0.48
    advantages
    0.47
    Activations Density 0.404%

    No Known Activations