© 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. 12-GEMMASCOPE-RES-16K
    11. 2754
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and conjunction-like phrases that often indicate clauses in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illumin
    -0.49
    subsid
    -0.48
    serious
    -0.47
    culti
    -0.46
     segíts
    -0.45
    ffions
    -0.44
     Anbieter
    -0.43
    amaño
    -0.42
    不同的
    -0.42
     aján
    -0.42
    POSITIVE LOGITS
    Rhestr
    0.43
     ApiException
    0.42
    assertIn
    0.41
     fairly
    0.41
     gainera
    0.40
    rungsseite
    0.40
     cellpadding
    0.39
    Secara
    0.38
     TextAppearance
    0.38
     finally
    0.37
    Activations Density 0.334%

    No Known Activations