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. 20-GEMMASCOPE-RES-16K
    6. 14364
    Prev
    Next
    INDEX
    Explanations

    expressions of possession or existence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Firstly
    -0.59
    yntaxException
    -0.56
     <>",
    -0.56
    Expectation
    -0.55
     Sơ
    -0.55
     Firstly
    -0.53
     Arrived
    -0.53
    FirebaseDatabase
    -0.51
    lisis
    -0.50
    Vía
    -0.50
    POSITIVE LOGITS
     always
    1.12
     never
    0.92
     historically
    0.91
     traditionally
    0.82
     since
    0.81
     often
    0.81
     repeatedly
    0.79
     consistently
    0.77
     sempre
    0.76
    always
    0.75
    Activations Density 0.300%

    No Known Activations