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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 2120
    Prev
    Next
    INDEX
    Explanations

    elements that represent numerical or computational values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    elements related to a specific concept or theme within a broader narrative

    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
    ParallelGroup
    -0.72
     ligiloj
    -0.59
     Seeder
    -0.59
     ivelany
    -0.59
     cathédrale
    -0.58
    AnimationsModule
    -0.58
    RenderAtEndOf
    -0.58
     sumpay
    -0.57
    Portály
    -0.56
     ExecuteAsync
    -0.56
    POSITIVE LOGITS
    TagMode
    0.83
     skills
    0.66
     skill
    0.61
     stunts
    0.55
     stunt
    0.54
    skill
    0.53
     moves
    0.51
    skills
    0.51
     Phaser
    0.50
    skilled
    0.49
    Activations Density 0.111%

    No Known Activations