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. 24-GEMMASCOPE-RES-16K
    6. 12727
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to trusts and beneficiaries

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

    Sentences related to legal or regulatory matters

    np_acts-logits-general · gemini-2.0-flash

    legal citations after periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.55
    ThroughAttribute
    -0.55
    ENSIS
    -0.54
     Beautiful
    -0.50
     Menschheit
    -0.49
    urture
    -0.49
    Diweddarwch
    -0.48
    usercontent
    -0.48
    gebracht
    -0.47
     محفوظة
    -0.47
    POSITIVE LOGITS
    Under
    1.05
     under
    0.99
     Under
    0.98
    under
    0.84
     Section
    0.79
     Failure
    0.78
    Section
    0.77
     anyone
    0.76
     Pursuant
    0.76
    anyone
    0.75
    Activations Density 0.580%

    No Known Activations