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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 30135
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    can generalize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Doch
    -0.38
    ,
    -0.36
    Doch
    -0.36
    ,"
    -0.34
     resourceCulture
    -0.33
    )
    -0.33
     The
    -0.33
    </em>
    -0.33
    </i>
    -0.32
     morceau
    -0.32
    POSITIVE LOGITS
     للمعارف
    0.83
     autorytatywna
    0.69
     témoig
    0.65
    Derbyniad
    0.63
    iſchen
    0.63
     Administrativna
    0.62
     AssemblyTitle
    0.62
     שוליים
    0.60
    niſſe
    0.60
    fromnode
    0.59
    Activations Density 0.106%

    No Known Activations