© 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. 13895
    Prev
    Next
    INDEX
    Explanations

    references to traditional media, particularly newspapers, and their role in communication

    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
    PreferredItem
    -0.70
    jsonwebtoken
    -0.66
     IBOutlet
    -0.61
    <bos>
    -0.61
     kaynağından
    -0.59
     InputDecoration
    -0.56
    rawDesc
    -0.54
    AndEndTag
    -0.53
    znál
    -0.53
    ContentAlignment
    -0.53
    POSITIVE LOGITS
    Xna
    0.52
     typique
    0.51
     mergeFrom
    0.50
     ouverte
    0.50
     diferite
    0.50
    essoal
    0.49
     bäst
    0.49
     étrangère
    0.49
     Hiram
    0.47
     obligé
    0.47
    Activations Density 0.470%

    No Known Activations