© 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. 25-GEMMASCOPE-RES-16K
    11. 15903
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and courtroom contexts

    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
     adverts
    -0.66
     programmes
    -0.65
     fertiliser
    -0.60
     mobilisation
    -0.60
     Programmes
    -0.60
     personalised
    -0.60
     generalised
    -0.59
     realisation
    -0.58
     tumour
    -0.57
     honourable
    -0.57
    POSITIVE LOGITS
     multicolor
    0.46
     parlor
    0.44
    Și
    0.42
     GenerationType
    0.40
     enggak
    0.40
    Карьера
    0.39
    Еще
    0.38
     ее
    0.36
    canceled
    0.36
     așa
    0.36
    Activations Density 0.030%

    No Known Activations