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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3300
    Prev
    Next
    INDEX
    Explanations

    code constructs related to function definitions and scope management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     CreateTagHelper
    -0.79
     snippetHide
    -0.63
    脚注の使い方
    -0.60
    SequentialGroup
    -0.57
    DockStyle
    -0.56
    __":
    -0.55
     insuffisamment
    -0.54
     surla
    -0.52
    __":
    
    -0.51
    ſſung
    -0.51
    POSITIVE LOGITS
     Италијани
    0.41
     Савезне
    0.40
    protoimpl
    0.36
    床
    0.35
     mac
    0.35
    velocityY
    0.35
    المكان
    0.34
    OGND
    0.34
     provid
    0.33
    信
    0.33
    Activations Density 0.267%

    No Known Activations