© 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-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6545
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to order processing and tasks in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.43
     libere
    -0.39
     américains
    -0.35
     traditionnelle
    -0.35
     vermogen
    -0.35
     traditionnels
    -0.33
     primario
    -0.31
    RTCK
    -0.31
     japonaise
    -0.30
     provisoire
    -0.30
    POSITIVE LOGITS
     Autorizaciones
    0.71
    oa̍t
    0.67
    期刊论文
    0.61
    FormTagHelper
    0.61
     يتيمه
    0.60
    Hauptartikel
    0.59
    findpost
    0.58
    localVar
    0.57
    SBATCH
    0.56
    脚注の使い方
    0.56
    Activations Density 0.760%

    No Known Activations