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. 5-GEMMASCOPE-RES-16K
    6. 11788
    Prev
    Next
    INDEX
    Explanations

    legal references, specifically related to court cases and statutes

    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
    \}\\
    -0.66
    ciaż
    -0.65
    '}}>
    -0.63
    ']")
    -0.60
     mend
    -0.59
     DIF
    -0.57
    mText
    -0.56
    /}.
    -0.56
     "}";
    -0.56
    )}$.
    -0.56
    POSITIVE LOGITS
     Assn
    1.16
     مشين
    1.12
     Govt
    1.07
     للمعارف
    1.06
     Atty
    1.02
    ClientRect
    1.00
     govt
    0.99
    bootstrapcdn
    0.98
     Bros
    0.97
     Sgt
    0.96
    Activations Density 0.812%

    No Known Activations