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. 5850
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to semiconductor devices and their configurations

    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
    fromnode
    -0.63
    TabIndex
    -0.59
    matchCondition
    -0.59
     RequestMethod
    -0.59
     FontWeight
    -0.56
     numerus
    -0.56
     Normdatei
    -0.55
    SpringBootTest
    -0.54
     Gattung
    -0.52
    whatever
    -0.52
    POSITIVE LOGITS
     schematic
    1.34
     Schematic
    1.17
     diagram
    1.12
    Schematic
    1.11
     illustration
    1.06
     illustrating
    1.02
     Diagram
    1.00
     showing
    0.99
     Illustration
    0.98
     sche
    0.97
    Activations Density 1.222%

    No Known Activations