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. 24-GEMMASCOPE-RES-16K
    6. 8322
    Prev
    Next
    INDEX
    Explanations

    phrases related to the complexity of personal and social relationships

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

    "the" preceding a noun

    np_acts-logits-general · gemini-2.0-flash

    idiomatic phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disponibilités
    -0.74
     resourceCulture
    -0.64
     ftate
    -0.63
    حياته
    -0.62
     intptr
    -0.62
    OGND
    -0.61
     ioutil
    -0.60
     poches
    -0.60
     œil
    -0.59
    حياتها
    -0.59
    POSITIVE LOGITS
     proverbial
    1.03
     metaphorical
    0.78
     figurative
    0.67
     sart
    0.55
     Epidemio
    0.55
     legislative
    0.51
     ideological
    0.51
     bureaucratic
    0.51
    Regulatory
    0.51
     theological
    0.51
    Activations Density 0.411%

    No Known Activations