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. 5-GEMMASCOPE-RES-16K
    6. 14313
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicative of quotes or speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.12
    ViewFeatures
    -1.08
     Reſ
    -1.02
     Majefty
    -1.01
    principalColumn
    -0.99
     iſt
    -0.97
     houſe
    -0.97
     faſt
    -0.94
    Према
    -0.94
     ProtoMessage
    -0.93
    POSITIVE LOGITS
     further
    0.72
     
    0.65
    further
    0.63
    "
    0.62
    I
    0.60
    Further
    0.59
     ayrıca
    0.56
     Further
    0.55
     I
    0.54
    ...
    0.54
    Activations Density 0.039%

    No Known Activations