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. 65769
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'x' in various contexts, particularly in relation to programming or code

    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
     الرياضيه
    -0.61
    ⓧ
    -0.60
    errHandler
    -0.57
    ExtendWith
    -0.57
    Bibliograf
    -0.56
    Демографія
    -0.56
     صوتيه
    -0.52
    balleur
    -0.52
    UrlResolution
    -0.52
    portál
    -0.51
    POSITIVE LOGITS
     debole
    0.35
    ckså
    0.34
     member
    0.34
    enumi
    0.32
     butts
    0.32
     împre
    0.32
    endregion
    0.30
    やった
    0.30
     normalen
    0.30
    greenrobot
    0.30
    Activations Density 0.003%

    No Known Activations