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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5357
    Prev
    Next
    INDEX
    Explanations

    commands and operations related to creating, updating, or deleting records in a database or application context

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

    programming commands related to creating or updating data structures.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    __*/
    -0.47
    webElementXpaths
    -0.44
     disambiguazione
    -0.43
    RefNanny
    -0.43
    localtime
    -0.42
    udsman
    -0.42
    jkl
    -0.42
     gus
    -0.41
     ?>>
    -0.41
     déjà
    -0.41
    POSITIVE LOGITS
    CreateModel
    0.62
     nových
    0.55
     nowych
    0.50
     nocturno
    0.50
    Creation
    0.50
     nowego
    0.49
     nový
    0.48
    OrUpdate
    0.48
     new
    0.47
     nocturna
    0.47
    Activations Density 0.132%

    No Known Activations