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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15816
    Prev
    Next
    INDEX
    Explanations

    references to political accountability and criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     محفوظة
    -0.75
    μβρίου
    -0.65
    ngdoc
    -0.65
     piede
    -0.63
    tvguidetime
    -0.62
    NewGuid
    -0.62
     contextLoads
    -0.60
     entanto
    -0.59
    nextProps
    -0.56
    ISODE
    -0.56
    POSITIVE LOGITS
    SourceChecksum
    1.03
    ագրություններ
    0.80
     nahilalakip
    0.72
     <<<<<<<<<<<<<<
    0.64
     المعيارى
    0.61
     disponibilités
    0.61
    awtextra
    0.59
     //$
    0.58
    漏
    0.57
     autorytatywna
    0.55
    Activations Density 0.321%

    No Known Activations