© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5867
    Prev
    Next
    INDEX
    Explanations

    phrases that express justification or reasoning behind actions and decisions

    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
    scrapy
    -0.72
     jadx
    -0.67
    PYX
    -0.66
    رشف
    -0.64
     trataba
    -0.63
    erialization
    -0.63
     كومونز
    -0.62
     ferons
    -0.62
    fjspx
    -0.61
     وتسجيلات
    -0.61
    POSITIVE LOGITS
     reason
    1.69
     reasons
    1.61
    reason
    1.57
     Reasons
    1.53
    Reason
    1.53
     Reason
    1.51
    Reasons
    1.49
    reasons
    1.49
     why
    1.38
     REASON
    1.34
    Activations Density 0.256%

    No Known Activations