Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12928
    Prev
    Next
    INDEX
    Explanations

    phrases conveying qualities of individuals, particularly with a focus on relationships and family connections

    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
    ratulations
    -0.81
    ikiki
    -0.74
    drawal
    -0.71
    BrowserModule
    -0.70
    elry
    -0.68
    duled
    -0.68
    eabouts
    -0.68
     chi̍t
    -0.68
    orneys
    -0.68
    culously
    -0.68
    POSITIVE LOGITS
    <eos>
    0.77
     diatas
    0.69
    UnusedPrivate
    0.68
    Firstly
    0.63
     kaarangay
    0.61
    OGND
    0.60
     Firstly
    0.58
    esinde
    0.58
     advices
    0.57
    useEffect
    0.56
    Activations Density 0.137%

    No Known Activations