© 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. 7-GEMMASCOPE-RES-16K
    11. 16175
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "state" and its variations in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.65
    oredCriteria
    -0.59
     noDo
    -0.58
    
    -0.58
    Życiorys
    -0.57
     doInBackground
    -0.54
    uxxxx
    -0.54
    tagHelperRunner
    -0.54
    FunctionFlags
    -0.52
    XmlAccessType
    -0.50
    POSITIVE LOGITS
     state
    2.30
     State
    2.22
    State
    2.08
     STATE
    1.95
    state
    1.93
    STATE
    1.77
     ſtate
    1.66
     ftate
    1.66
     states
    1.41
    getState
    1.35
    Activations Density 0.119%

    No Known Activations