© 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. 36-GEMMASCOPE-RES-16K
    11. 7557
    Prev
    Next
    INDEX
    Explanations

    the use of the present perfect tense in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.57
    hoeddwyd
    -0.48
     tagit
    -0.47
     ब्रेकडाउन
    -0.47
     Brought
    -0.47
    География
    -0.47
    discovered
    -0.47
    SharedDtor
    -0.46
    kháu
    -0.46
     disambiguazione
    -0.46
    POSITIVE LOGITS
     been
    1.64
     was
    1.35
     был
    0.96
     be
    0.94
     была
    0.93
     were
    0.92
     было
    0.90
     buvo
    0.89
     été
    0.88
     było
    0.87
    Activations Density 0.233%

    No Known Activations