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. 2-GEMMASCOPE-RES-16K
    6. 6391
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -0.82
    Portail
    -0.78
     ſeveral
    -0.77
     وتسجيلات
    -0.73
     houſe
    -0.73
     Arxivat
    -0.71
    melhor
    -0.71
     allarg
    -0.70
     greateſt
    -0.69
     wikipagina
    -0.69
    POSITIVE LOGITS
     un
    2.75
     uns
    1.50
     unt
    1.50
     Un
    1.42
     una
    1.41
     ung
    1.33
     une
    1.27
    Un
    1.25
     Uns
    1.10
    un
    1.10
    Activations Density 0.053%

    No Known Activations