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. 20-GEMMASCOPE-RES-16K
    6. 554
    Prev
    Next
    INDEX
    Explanations

    references to electrical components and their connections in circuits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.67
     surla
    -0.66
     JpaRepository
    -0.64
    Rhestr
    -0.62
    .*")]
    -0.61
    ſelf
    -0.60
     juſ
    -0.60
     poffe
    -0.60
    Kjelder
    -0.60
    RTSC
    -0.59
    POSITIVE LOGITS
     ground
    1.24
     Ground
    1.16
    ground
    1.13
    Ground
    1.10
     GROUND
    1.10
     grounding
    0.99
     GND
    0.92
     grounded
    0.91
    GROUND
    0.90
    Grounded
    0.87
    Activations Density 0.359%

    No Known Activations