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

    Neuronpedia

    Jacobian LensNEW
    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. 15-GEMMASCOPE-RES-16K
    11. 6584
    Prev
    Next
    INDEX
    Explanations

    references to loss, transformation, and the impact of substances on people and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.78
    Personendaten
    -0.66
    icina
    -0.65
     supplies
    -0.55
    }());
    -0.55
    quirrel
    -0.54
     chi̍t
    -0.53
     suppliers
    -0.51
     autorytatywna
    -0.51
    Hintergrund
    -0.50
    POSITIVE LOGITS
     unrecogn
    1.16
     transformed
    0.84
     resemblance
    0.82
     transformation
    0.73
     resemble
    0.71
    transformed
    0.69
     resembles
    0.68
     ressemb
    0.68
     ressemble
    0.67
    transformation
    0.65
    Activations Density 0.230%

    No Known Activations