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. 17-GEMMASCOPE-RES-65K
    6. 28382
    Prev
    Next
    INDEX
    Explanations

    mentions of poverty and nutritional deficiencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    consulté
    -0.54
    AnchorStyles
    -0.50
     Paglinawan
    -0.50
     thiệu
    -0.47
    ukah
    -0.47
    styleUrls
    -0.46
     CP
    -0.45
    good
    -0.45
    figsize
    -0.44
    saraba
    -0.44
    POSITIVE LOGITS
     SwitchCompat
    0.69
     poverty
    0.65
    Poverty
    0.65
     Poverty
    0.62
    NewUrlParser
    0.59
     OFDb
    0.59
     living
    0.58
    enumi
    0.58
    poverty
    0.58
     poorest
    0.58
    Activations Density 0.071%

    No Known Activations