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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6456
    Prev
    Next
    INDEX
    Explanations

    elements related to metaphorical constructs and social commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     associées
    -0.44
     köz
    -0.41
     associés
    -0.40
     Rahmen
    -0.40
     achten
    -0.39
     passés
    -0.38
     terület
    -0.38
    abadi
    -0.38
     Körpers
    -0.37
    setUse
    -0.36
    POSITIVE LOGITS
    contentLoaded
    1.11
    تقاوى
    1.06
     metaphorical
    1.00
    StructEnd
    0.95
     metaphor
    0.94
    parsedMessage
    0.93
     proverbial
    0.92
     betweenstory
    0.87
     oprot
    0.86
     protoimpl
    0.86
    Activations Density 0.391%

    No Known Activations