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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 14972
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms related to medical terminology and health data

    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
    MessageTagHelper
    -0.37
     nourrir
    -0.31
    espère
    -0.30
     snippetHide
    -0.29
     reprendre
    -0.29
    muda
    -0.29
     lemn
    -0.28
    aktery
    -0.28
     rodas
    -0.28
     garçon
    -0.28
    POSITIVE LOGITS
     Normdatei
    0.77
     betweenstory
    0.72
    IndentedString
    0.65
    قایناق‌لار
    0.63
     autorytatywna
    0.63
    Autoritní
    0.57
     Савезне
    0.56
    OGND
    0.55
    ſt
    0.53
     Administrativna
    0.52
    Activations Density 1.657%

    No Known Activations