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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 2386
    Prev
    Next
    INDEX
    Explanations

    concepts related to relational dynamics and connections between entities

    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
     WaitForSeconds
    -0.61
     Eleg
    -0.57
    :✨
    -0.57
    canestro
    -0.55
    Appe
    -0.55
    anguardia
    -0.55
     fontSize
    -0.55
     noires
    -0.54
     extré
    -0.53
     chapéu
    -0.53
    POSITIVE LOGITS
     relationship
    1.75
     relation
    1.64
     relations
    1.59
     relationships
    1.57
     Relationship
    1.55
    relationship
    1.54
    Relationship
    1.49
     RELATIONSHIP
    1.45
     Relation
    1.43
     RELATION
    1.43
    Activations Density 0.300%

    No Known Activations