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. 16-GEMMASCOPE-RES-16K
    6. 2932
    Prev
    Next
    INDEX
    Explanations

    terms related to social support and rehabilitation programs

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

    Rehabilitation, recovery, and self-sufficiency

    np_acts-logits-general · gemini-2.0-flash

    rehabilitation and self-sufficiency through opportunities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.71
     resourceCulture
    -0.57
    LookAnd
    -0.57
     CreateTagHelper
    -0.57
    Bronnen
    -0.57
     unknownFields
    -0.55
    ⓘ
    -0.54
    KommentareTeilen
    -0.53
    DoubleQuotes
    -0.53
    ConverterFactory
    -0.50
    POSITIVE LOGITS
     rehabilit
    1.02
     rehabilitation
    1.01
     Rehabilitation
    0.88
     rehabilitate
    0.87
     rehab
    0.79
     Rehab
    0.78
     vocational
    0.75
    habilitation
    0.72
    自立
    0.68
     Vocational
    0.66
    Activations Density 0.419%

    No Known Activations