Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23-GEMMASCOPE-RES-16K
    6. 12435
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "in a" or "a" in various contexts within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.60
    SharedCtor
    -0.60
     متعلقه
    -0.59
    expandindo
    -0.59
    ContentAsync
    -0.56
    lectic
    -0.55
     >=",
    -0.54
    Vidite
    -0.51
     MenuView
    -0.49
    writerow
    -0.48
    POSITIVE LOGITS
     interview
    0.70
     telephone
    0.69
     recent
    0.67
     appearance
    0.66
     speech
    0.66
    twimg
    0.66
     phone
    0.65
     exclusive
    0.63
    complexContent
    0.62
     televised
    0.61
    Activations Density 0.268%

    No Known Activations