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. 14947
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and conditions of office retention

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

    relating to "renewal" or "reelection"

    np_acts-logits-general · gemini-2.0-flash

    renewal and extensions

    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
    GEBURTSDATUM
    -0.65
    Collegamenti
    -0.57
    espół
    -0.52
    zzati
    -0.50
    batterie
    -0.50
     المعيارى
    -0.49
     Hadrian
    -0.49
    izarro
    -0.49
    FormTagHelper
    -0.48
    uated
    -0.48
    POSITIVE LOGITS
     renewal
    1.86
     renew
    1.70
     renewing
    1.65
     renewals
    1.63
     extension
    1.57
     extensions
    1.51
     Renewal
    1.49
    renewal
    1.45
    renew
    1.44
    Renewal
    1.41
    Activations Density 0.224%

    No Known Activations