© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9194
    Prev
    Next
    INDEX
    Explanations

    sequence of actions and events within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Past tense verbs or states

    np_acts-logits-general · gemini-2.0-flash

    actions completed or underway

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __))
    -0.64
    aarrggbb
    -0.63
     when
    -0.62
     CreateTagHelper
    -0.61
     когда
    -0.61
     MainAxisSize
    -0.59
     OnInit
    -0.57
    ंदीखरीदारी
    -0.56
    __);
    -0.54
     sobald
    -0.54
    POSITIVE LOGITS
     nanti
    0.42
     xong
    0.40
    它們
    0.40
    Références
    0.36
     decides
    0.35
    它们
    0.35
     InputDecoration
    0.34
     очеред
    0.33
     aceptas
    0.33
    niająca
    0.33
    Activations Density 0.820%

    No Known Activations