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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 3106
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to legal ownership rights and beneficiary status in contracts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Legal and financial "rights" and "interests"

    np_acts-logits-general · gemini-2.0-flash

    rights and interests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cherchés
    -0.64
    HideFlags
    -0.60
    amoan
    -0.58
     gyhoeddwyd
    -0.55
    WithFormat
    -0.54
     Ouverture
    -0.54
    Життєпис
    -0.53
    ValueGeneration
    -0.52
     Laughter
    -0.51
    SourceChecksum
    -0.50
    POSITIVE LOGITS
     rights
    1.16
    rights
    1.06
     right
    0.99
     RIGHTS
    0.93
     Rights
    0.93
     claims
    0.89
     claim
    0.88
     Right
    0.88
     diritti
    0.86
     droit
    0.85
    Activations Density 0.599%

    No Known Activations