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. 25-GEMMASCOPE-RES-16K
    6. 5933
    Prev
    Next
    INDEX
    Explanations

    significant plot points and character motivations in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.59
    AddTagHelper
    -0.55
    tvguidetime
    -0.53
    LookAnd
    -0.51
    lido
    -0.51
    ynomial
    -0.50
    EndProject
    -0.49
     Floren
    -0.49
     commissioned
    -0.49
    archiviato
    -0.48
    POSITIVE LOGITS
     plot
    1.13
     subplot
    0.96
     storyline
    0.91
     exposition
    0.88
     backstory
    0.86
    plot
    0.85
     storylines
    0.84
     PLOT
    0.84
     Plot
    0.82
     foreshadow
    0.81
    Activations Density 0.515%

    No Known Activations