© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15723
    Prev
    Next
    INDEX
    Explanations

    instances of accidental actions or unintentional events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    λευτα
    -0.44
     tendance
    -0.36
    FLAGS
    -0.34
    mybatisplus
    -0.34
     här
    -0.33
    ODB
    -0.33
    لينكات
    -0.33
    rizona
    -0.33
     anges
    -0.33
    isabeth
    -0.32
    POSITIVE LOGITS
     accidentally
    1.30
     accidental
    1.19
    accident
    1.12
     accident
    1.09
     Accidental
    1.05
     inadvertently
    1.02
    Accidental
    1.02
     inadvert
    1.01
     Accident
    0.96
     ACCIDENT
    0.96
    Activations Density 0.485%

    No Known Activations