© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 3977
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal requirements and governmental procedures

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

    legality or rules

    np_acts-logits-general · gemini-2.0-flash

    legal clauses and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -0.63
     særlig
    -0.60
    الحياه
    -0.59
     Verder
    -0.58
     Mitar
    -0.55
     thèmes
    -0.53
     vooral
    -0.52
    UrlResolution
    -0.52
     насељу
    -0.51
     diversify
    -0.50
    POSITIVE LOGITS
     legally
    1.44
     legal
    1.30
     legality
    1.20
    legal
    1.18
     technically
    1.06
    Technically
    1.04
     Legal
    1.03
     légal
    1.03
     Technically
    1.03
    Legal
    0.99
    Activations Density 0.789%

    No Known Activations