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. 23-GEMMASCOPE-RES-16K
    6. 12387
    Prev
    Next
    INDEX
    Explanations

    scientific variables and parameters associated with cosmological and physical models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orrho
    -0.48
     Márquez
    -0.46
    AddHtmlAttribute
    -0.43
    RIQUE
    -0.41
    おめでとう
    -0.41
    timedia
    -0.41
     champagne
    -0.40
    monk
    -0.40
    扈
    -0.39
     tron
    -0.39
    POSITIVE LOGITS
     negative
    2.42
     Negative
    2.38
    Negative
    2.33
    negative
    2.26
     NEGATIVE
    2.07
     (-
    1.99
     Positive
    1.97
     positive
    1.94
    NEGATIVE
    1.89
     négatif
    1.89
    Activations Density 2.729%

    No Known Activations