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. 5-GEMMASCOPE-RES-16K
    6. 16134
    Prev
    Next
    INDEX
    Explanations

    structural or categorical information related to entities in datasets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _{-\
    -0.61
    UIFont
    -0.59
    /#{
    -0.56
     confronti
    -0.56
    orth
    -0.56
    iforn
    -0.52
    \{(
    -0.51
    tiska
    -0.50
    impinan
    -0.50
    :</
    -0.50
    POSITIVE LOGITS
    createStatement
    0.90
    MessageTagHelper
    0.82
    Personendaten
    0.77
     ivelany
    0.74
     препратки
    0.73
     bezeichneter
    0.72
    endphp
    0.72
     الحره
    0.69
    省市镇
    0.67
    enderror
    0.67
    Activations Density 1.115%

    No Known Activations