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. 2-GEMMASCOPE-RES-16K
    6. 1106
    Prev
    Next
    INDEX
    Explanations

    references to property owners or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]-->
    -0.69
    المناصب
    -0.67
    addCriterion
    -0.66
     periodistas
    -0.66
    jarat
    -0.66
     ángeles
    -0.63
    ulados
    -0.62
     considérable
    -0.61
    deu
    -0.60
     digress
    -0.59
    POSITIVE LOGITS
     owners
    3.29
     owner
    3.27
     Owners
    3.04
     Owner
    2.98
    owner
    2.98
    Owner
    2.86
    Owners
    2.83
    owners
    2.81
     OWNER
    2.75
    OWNER
    2.56
    Activations Density 0.060%

    No Known Activations