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. 22-GEMMASCOPE-RES-16K
    6. 5860
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to trusts and beneficiaries

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

    Legal and financial matters related to estates

    np_acts-logits-general · gemini-2.0-flash

    estate and inheritance law

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.61
     AssemblyCulture
    -0.58
     sumpay
    -0.54
     Galile
    -0.53
    ipedi
    -0.52
    Portail
    -0.50
     [*]
    -0.47
    帖最后由
    -0.47
    tagHelperRunner
    -0.47
    uberge
    -0.45
    POSITIVE LOGITS
     estate
    1.35
     Estate
    1.24
     executor
    1.16
    Estate
    1.15
    estate
    1.14
     probate
    1.14
     testamento
    1.12
     inheritance
    1.10
     executors
    1.08
     ESTATE
    1.06
    Activations Density 0.474%

    No Known Activations