© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 12707
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions or preferences in decision-making context

    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
     Biôgrafia
    -0.59
     femininas
    -0.56
     milliers
    -0.54
     constantly
    -0.50
    Soon
    -0.49
     aidé
    -0.48
     ladr
    -0.48
     centaines
    -0.48
     meren
    -0.48
     nemico
    -0.47
    POSITIVE LOGITS
     opt
    1.20
     opting
    1.10
     opted
    1.10
     stick
    1.09
     sticking
    0.99
     Opt
    0.99
     Stick
    0.97
     opts
    0.95
    Stick
    0.94
    Opt
    0.91
    Activations Density 0.408%

    No Known Activations