© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 659
    Prev
    Next
    INDEX
    Explanations

    terms related to hierarchy and control structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Grüsse
    -0.43
    躇
    -0.35
     manžel
    -0.35
    Conclusão
    -0.35
     kontaktu
    -0.35
     Gästen
    -0.35
     mourut
    -0.35
     Wikiseite
    -0.34
    httphttps
    -0.34
     consecuencia
    -0.34
    POSITIVE LOGITS
     Master
    1.23
     master
    1.20
     MASTER
    1.17
    Master
    1.09
    master
    0.98
     masters
    0.95
    MASTER
    0.93
     Masters
    0.90
    Masters
    0.89
     マスター
    0.84
    Activations Density 0.045%

    No Known Activations