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. 65964
    Prev
    Next
    INDEX
    Explanations

    instances of ownership and possession in the context of information use

    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
     propOrder
    -0.61
    DataPropertyName
    -0.57
    ngdoc
    -0.57
    saraba
    -0.56
     StringTokenizer
    -0.55
    styleType
    -0.54
     <=",
    -0.51
     defaultstate
    -0.51
    olata
    -0.50
    kloped
    -0.50
    POSITIVE LOGITS
    #+#
    0.48
    awtextra
    0.43
     okuyayım
    0.43
     féminin
    0.38
     contextLoads
    0.37
    ↵↵↵↵↵
    0.37
     externi
    0.36
     ).
    0.36
    """.
    0.36
    NUMX
    0.35
    Activations Density 0.000%

    No Known Activations