© 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. 40-GEMMASCOPE-RES-16K
    6. 1760
    Prev
    Next
    INDEX
    Explanations

    terms related to legal actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wako
    -0.46
     للمعارف
    -0.43
     Tab
    -0.43
    引起的
    -0.43
     noDo
    -0.42
    AnchorStyles
    -0.40
    Tab
    -0.40
    Topping
    -0.40
     tev
    -0.40
     melding
    -0.40
    POSITIVE LOGITS
     hurt
    0.81
     hurts
    0.74
     disadvantage
    0.72
     negatively
    0.72
     penal
    0.71
     harm
    0.70
     hurting
    0.66
     adversely
    0.65
     harmed
    0.64
     hob
    0.63
    Activations Density 0.615%

    No Known Activations