© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 8162
    Prev
    Next
    INDEX
    Explanations

    phrases related to loss and consequences

    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
     nemlig
    -0.67
     noastră
    -0.65
     vanske
    -0.65
     männis
    -0.63
     vicenda
    -0.62
    "—
    -0.62
     faccia
    -0.60
     ſta
    -0.59
     kvinna
    -0.59
     fråga
    -0.58
    POSITIVE LOGITS
     yoy
    0.64
     thier
    0.61
     thay
    0.61
     espect
    0.56
     encu
    0.56
     yo
    0.55
     foe
    0.55
     upto
    0.54
     threw
    0.53
     handel
    0.53
    Activations Density 0.652%

    No Known Activations