© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 8801
    Prev
    Next
    INDEX
    Explanations

    numerical values and references to file types or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     greateſt
    -0.93
     itſelf
    -0.90
     unſ
    -0.89
     Cæsar
    -0.87
     purpoſe
    -0.84
     perſon
    -0.84
     pleaſure
    -0.82
     myſelf
    -0.81
     neceff
    -0.81
     Monfieur
    -0.81
    POSITIVE LOGITS
     Al
    0.52
    Ligações
    0.49
     van
    0.47
    bmatrix
    0.47
     Ca
    0.47
     nei
    0.46
     al
    0.46
    críbete
    0.45
    vo
    0.45
    rep
    0.45
    Activations Density 0.056%

    No Known Activations