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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-GEMMASCOPE-RES-16K
    6. 13474
    Prev
    Next
    INDEX
    Explanations

    words related to ownership and possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.76
    醐
    -0.72
    matchCondition
    -0.71
     jsPsych
    -0.70
    ergies
    -0.70
     '\\;'
    -0.69
    EventId
    -0.69
    Jax
    -0.66
    AddTagHelper
    -0.66
     Everglades
    -0.66
    POSITIVE LOGITS
     owned
    1.72
    owned
    1.53
     ownership
    1.51
     Owned
    1.49
     owns
    1.48
     owning
    1.46
    Owned
    1.41
     Ownership
    1.37
    ownership
    1.35
    owning
    1.28
    Activations Density 0.103%

    No Known Activations