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. 12-GEMMASCOPE-RES-16K
    6. 657
    Prev
    Next
    INDEX
    Explanations

    elements related to introductions and names in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.76
     CiNii
    -0.54
    
    -0.53
    +#+#
    -0.51
    licópter
    -0.49
    ocation
    -0.49
    oult
    -0.48
    riwal
    -0.48
    ваете
    -0.46
     Ohr
    -0.45
    POSITIVE LOGITS
    قایناقلار
    0.67
     postIndex
    0.63
    $_['
    0.60
     fieldNum
    0.57
    localctx
    0.57
    setopt
    0.57
    setupUi
    0.55
     محفوظة
    0.55
     aisle
    0.55
    JspWriter
    0.54
    Activations Density 1.053%

    No Known Activations