Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11673
    Prev
    Next
    INDEX
    Explanations

    technical coding language elements and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -0.54
    oneofs
    -0.52
    getColumnIndex
    -0.50
    ➌
    -0.49
    TintMode
    -0.48
    DataPropertyName
    -0.45
    wpi
    -0.45
    haikusbot
    -0.45
     OFDb
    -0.45
    AlterField
    -0.44
    POSITIVE LOGITS
     مشين
    0.60
    multirow
    0.55
    脚注の使い方
    0.45
    PYX
    0.44
    存于互联网档案馆
    0.42
     تانيه
    0.42
     Gründung
    0.41
     absorción
    0.41
     دیکھیے
    0.41
     ogrom
    0.40
    Activations Density 0.035%

    No Known Activations