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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 8132
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the importance or significance of certain ideas or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.74
     doubtnut
    -0.72
     garda
    -0.72
     Majefty
    -0.70
    ;");
    -0.65
    iconque
    -0.65
     conch
    -0.63
     Moz
    -0.63
     sèche
    -0.63
    ❋
    -0.63
    POSITIVE LOGITS
     it
    0.64
     easier
    0.61
    rungsseite
    0.59
     It
    0.55
     its
    0.55
     time
    0.54
     snowing
    0.54
     happening
    0.53
    ίνεται
    0.53
     emoción
    0.52
    Activations Density 0.392%

    No Known Activations