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

    Neuronpedia

    APICircuit 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. 13-GEMMASCOPE-RES-16K
    6. 7629
    Prev
    Next
    INDEX
    Explanations

    words indicating comparisons or distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    发表于
    -0.63
     consultato
    -0.52
    SBC
    -0.50
    ADVERTISEMENT
    -0.49
     Tenggara
    -0.49
    MENAFN
    -0.47
    brainly
    -0.47
    Билгалдахарш
    -0.46
    ANSA
    -0.46
    triggered
    -0.46
    POSITIVE LOGITS
     deviations
    0.98
     deviation
    0.96
     Abweich
    0.95
     deviate
    0.85
    viations
    0.81
     Deviation
    0.78
    Deviation
    0.71
     AssemblyCulture
    0.71
     откло
    0.65
     discrepancies
    0.64
    Activations Density 0.540%

    No Known Activations