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
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65874
    Prev
    Next
    INDEX
    Explanations

    structured data and XML elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.62
    +#+
    -0.57
     noDo
    -0.56
    ClInclude
    -0.49
     كومونز
    -0.48
    PYX
    -0.47
     geprek
    -0.47
    MethodManager
    -0.47
    VYMaps
    -0.47
    matchCondition
    -0.46
    POSITIVE LOGITS
    ADELPHIA
    0.40
     Ser
    0.35
     Serial
    0.33
     Tee
    0.32
     Sab
    0.32
     programme
    0.31
     ]
    
    0.30
    ̍
    0.30
     SERIAL
    0.30
    Ser
    0.29
    Activations Density 0.001%

    No Known Activations