© 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. 10-GEMMASCOPE-RES-16K
    11. 10601
    Prev
    Next
    INDEX
    Explanations

    repetitive mathematical terms and configurations, particularly in a computational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h3>
    -0.53
    </strong>
    -0.49
    MessageOf
    -0.45
    敷
    -0.43
    wp
    -0.43
    </h1>
    -0.43
     cons
    -0.42
     «
    -0.42
    eningen
    -0.42
     po
    -0.41
    POSITIVE LOGITS
     itſelf
    1.01
     myſelf
    1.00
    uxxxx
    0.87
     ་་
    0.83
    AddTagHelper
    0.81
     iſt
    0.81
     ſeveral
    0.79
     Efq
    0.79
    ſelves
    0.78
    Obrázky
    0.78
    Activations Density 1.970%

    No Known Activations