© 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-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 10955
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and states of being in the context of relationships and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     samostat
    -0.47
     množství
    -0.44
     samodziel
    -0.44
    nosaurus
    -0.44
    TacToe
    -0.43
     vectorielles
    -0.43
    Godzilla
    -0.42
     odpově
    -0.41
     chrétiens
    -0.41
     undersø
    -0.41
    POSITIVE LOGITS
     John
    0.81
     Dr
    0.77
     David
    0.73
     Michael
    0.66
     J
    0.64
     propOrder
    0.63
     Alex
    0.62
     Joe
    0.61
     Richard
    0.61
     Mike
    0.61
    Activations Density 4.675%

    No Known Activations