© 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-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9319
    Prev
    Next
    INDEX
    Explanations

    phrases indicating progress and adaptation in experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 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
     ब्रेकडाउन
    -0.52
    thâu
    -0.49
     propOrder
    -0.49
     referenties
    -0.48
    Rohy
    -0.47
     estekak
    -0.45
    InputTagHelper
    -0.45
    AxisSize
    -0.44
    aarrggbb
    -0.44
    HostException
    -0.43
    POSITIVE LOGITS
    慣れて
    0.67
    慣
    0.66
     gradually
    0.59
     mastered
    0.56
     familiarity
    0.56
     Gradually
    0.55
     settled
    0.53
     habitu
    0.50
     allmäh
    0.50
     slowly
    0.49
    Activations Density 0.324%

    No Known Activations