© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 4613
    Prev
    Next
    INDEX
    Explanations

    specific phrases and structures related to obligations and conditions in agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.82
    पया
    -0.81
     Majefty
    -0.78
     purpoſe
    -0.78
     kaarangay
    -0.76
     uſe
    -0.75
     pleaſure
    -0.73
     Roskov
    -0.72
     sumpay
    -0.70
     RIPRODUZIONE
    -0.69
    POSITIVE LOGITS
     Made
    0.60
     Tra
    0.59
     Str
    0.59
     App
    0.59
     Sp
    0.57
     Re
    0.57
     Sto
    0.56
     Rec
    0.56
     Tos
    0.56
     St
    0.55
    Activations Density 0.353%

    No Known Activations