© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5455
    Prev
    Next
    INDEX
    Explanations

    elements related to XML schemas and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poffe
    -0.95
     poffible
    -0.94
    #+#
    -0.85
    CreateModel
    -0.80
     Jefus
    -0.77
     Vienne
    -0.77
    IContainer
    -0.77
     fhort
    -0.76
     becauſe
    -0.74
     poff
    -0.74
    POSITIVE LOGITS
     SCHE
    1.26
    SCHEMA
    1.18
     sche
    1.17
     SCHEME
    1.15
    Schema
    1.15
     Schema
    1.14
    scheme
    1.13
     Schemes
    1.13
     schema
    1.11
     Sche
    1.09
    Activations Density 0.196%

    No Known Activations