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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 768
    Prev
    Next
    INDEX
    Explanations

    terms related to vulnerability and at-risk populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms related to vulnerability and at-risk populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    vulnerable people or groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ⓧ
    -1.00
     صوتيه
    -0.92
    TypedDataSet
    -0.90
    :✨
    -0.86
     gynhyrchwyd
    -0.81
    PyErr
    -0.81
    ValueStyle
    -0.81
    enterOuterAlt
    -0.80
    protoimpl
    -0.80
    DotNetBar
    -0.75
    POSITIVE LOGITS
     vulnerabilities
    0.87
    nerable
    0.85
     vulnerability
    0.79
     VUL
    0.77
    vul
    0.76
     Vul
    0.75
    nerability
    0.74
    Vul
    0.72
     Vulnerable
    0.71
     vulner
    0.71
    Activations Density 0.012%

    No Known Activations