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. 65935
    Prev
    Next
    INDEX
    Explanations

    geological features and terms related to volcanic formations

    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
    Története
    -0.48
     numerus
    -0.46
    nosaurus
    -0.44
    UnusedPrivate
    -0.42
    Bakgrunnsstoff
    -0.41
    riculum
    -0.39
     desal
    -0.39
    Boh
    -0.39
     Eman
    -0.38
    verwijspagina
    -0.38
    POSITIVE LOGITS
     metamorphic
    0.69
     metamor
    0.63
     granite
    0.61
     intrusions
    0.55
     intrusive
    0.54
     rocks
    0.52
     méta
    0.50
     granito
    0.50
     rock
    0.49
     rocas
    0.49
    Activations Density 0.007%

    No Known Activations