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. 65778
    Prev
    Next
    INDEX
    Explanations

    phrases and categories related to prestigious architectural programs and honors

    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
     affez
    -0.46
     sudut
    -0.43
     popular
    -0.39
     invitamos
    -0.39
     rappeler
    -0.37
    seits
    -0.36
    <strong>
    -0.35
     ajuns
    -0.35
     промышленности
    -0.34
     demora
    -0.34
    POSITIVE LOGITS
     contextLoads
    0.73
     ſche
    0.67
    LookAnd
    0.65
    stylers
    0.59
     vectorstock
    0.53
     dreamstime
    0.53
     $_"
    0.53
     workplaces
    0.52
    DockStyle
    0.52
    tonode
    0.51
    Activations Density 0.034%

    No Known Activations