© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7385
    Prev
    Next
    INDEX
    Explanations

    verbs indicating past actions or experiences, especially those related to achieving or encountering something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.76
     verſ
    -0.70
     plufieurs
    -0.69
     ainfi
    -0.68
     ſch
    -0.66
     faſt
    -0.65
     ſtate
    -0.65
     vectorielles
    -0.65
     Perſ
    -0.65
     houſe
    -0.64
    POSITIVE LOGITS
     thrived
    0.78
     undertook
    0.76
     drifted
    0.76
     underwent
    0.76
     boasted
    0.75
    carried
    0.72
     triumphed
    0.72
     resisted
    0.72
     availed
    0.72
     mourned
    0.71
    Activations Density 0.741%

    No Known Activations