© 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. 5-GEMMASCOPE-RES-16K
    11. 5039
    Prev
    Next
    INDEX
    Explanations

    terms related to improvement or enhancement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itoneum
    -0.68
     Berufs
    -0.62
    AccessFile
    -0.60
    لكتر
    -0.59
     mem
    -0.58
    Esk
    -0.58
    tj
    -0.58
    Geography
    -0.57
    MethodManager
    -0.56
    issão
    -0.56
    POSITIVE LOGITS
     enhancement
    2.01
     enhancements
    2.00
     enhance
    1.89
    hancing
    1.89
     Enhance
    1.85
    Enhance
    1.82
    enhance
    1.82
     enhancing
    1.80
     Enhancement
    1.79
     enhanced
    1.73
    Activations Density 0.081%

    No Known Activations