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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12396
    Prev
    Next
    INDEX
    Explanations

    specific terms related to scientific experimental procedures and components

    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
     AssemblyProduct
    -0.60
    tagHelperRunner
    -0.59
     논
    -0.58
    ⓧ
    -0.57
     المعيارى
    -0.56
     jScrollPane
    -0.54
     digitais
    -0.54
    antation
    -0.52
    ❋
    -0.51
     Савезне
    -0.51
    POSITIVE LOGITS
     Tris
    0.63
    ValueGeneration
    0.63
     Earle
    0.58
    Tris
    0.57
    Complete
    0.57
     buffer
    0.56
    ydd
    0.55
     Complete
    0.54
     supplemented
    0.53
     PBS
    0.53
    Activations Density 1.298%

    No Known Activations