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. 25-GEMMASCOPE-RES-16K
    6. 5829
    Prev
    Next
    INDEX
    Explanations

    phrases related to commitment and support within communities and partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.92
     JUGA
    -0.48
    aspectj
    -0.48
    ngdoc
    -0.47
    Disliked
    -0.47
    getSystemService
    -0.47
     AssemblyCompany
    -0.46
    irms
    -0.45
    missed
    -0.45
    väg
    -0.44
    POSITIVE LOGITS
     assisted
    1.04
     helped
    1.04
     supported
    0.89
     aided
    0.88
    assisted
    0.80
     facilitated
    0.80
    helped
    0.76
     enabled
    0.76
     aidé
    0.75
     enhanced
    0.74
    Activations Density 0.459%

    No Known Activations