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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5453
    Prev
    Next
    INDEX
    Explanations

    methods related to data manipulation and processing in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sphase
    -0.49
    <bos>
    -0.45
    !
    -0.43
    Rhestr
    -0.42
     InputDecoration
    -0.42
    tonode
    -0.42
    hirts
    -0.40
     daher
    -0.38
    fromnode
    -0.38
    jsii
    -0.38
    POSITIVE LOGITS
     kaynağından
    0.99
     itſelf
    0.87
     myſelf
    0.81
     $_"
    0.78
     themſelves
    0.77
     оригіналу
    0.73
     doubtnut
    0.72
    modelBuilder
    0.72
     Monfieur
    0.72
    __":
    
    0.70
    Activations Density 0.385%

    No Known Activations