© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2841
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "por" in various contexts

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

    Following "por" or "par"

    np_acts-logits-general · gemini-2.0-flash

    por followed by qué, los, la, diante, contre

    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
     itſelf
    -1.23
     myſelf
    -1.22
     للاسماء
    -1.18
     Normdatei
    -1.18
     Cæsar
    -1.18
     Jefus
    -1.13
     Efq
    -1.13
     Houſe
    -1.09
     ―――――
    -1.09
     Anſ
    -1.07
    POSITIVE LOGITS
     por
    0.81
    por
    0.76
     Por
    0.66
     par
    0.63
     vin
    0.60
    Por
    0.58
     a
    0.56
     po
    0.55
     pol
    0.53
     n
    0.52
    Activations Density 0.036%

    No Known Activations