Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7941
    Prev
    Next
    INDEX
    Explanations

    comparative terms and phrases that highlight differences in qualities or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esía
    -0.66
    esModule
    -0.64
     EnglishChoose
    -0.64
    consulté
    -0.62
     Wikimedijinoj
    -0.61
    يكب
    -0.61
    caron
    -0.57
     매우
    -0.57
     Wikispecies
    -0.57
     voyons
    -0.57
    POSITIVE LOGITS
     than
    1.79
    than
    1.29
     tighter
    1.20
     stronger
    1.20
     THAN
    1.20
     clearer
    1.19
    Than
    1.17
     easier
    1.16
     hơn
    1.16
     safer
    1.15
    Activations Density 1.093%

    No Known Activations