© 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. 23-GEMMASCOPE-RES-16K
    11. 5391
    Prev
    Next
    INDEX
    Explanations

    references to articles and documents, particularly regarding their status and attributes

    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
    VIAF
    -0.72
     betweenstory
    -0.68
     Administrativna
    -0.66
     ویکی‌پدیا
    -0.64
    complexType
    -0.63
     détaillés
    -0.60
     rodea
    -0.59
    iettivo
    -0.59
    OGND
    -0.57
    RUnlock
    -0.56
    POSITIVE LOGITS
     sponsored
    0.85
     courtesy
    0.82
     originally
    0.76
     adapted
    0.69
     Sponsored
    0.67
     brought
    0.64
     contributed
    0.59
    originally
    0.59
    Hentet
    0.58
    brought
    0.58
    Activations Density 0.325%

    No Known Activations