Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14767
    Prev
    Next
    INDEX
    Explanations

    instances of the word "upon" and its context in various legal or evaluative statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anſ
    -0.91
    AndEndTag
    -0.87
     Reſ
    -0.86
     Houſe
    -0.85
     ſta
    -0.83
    󠁣
    -0.81
     صوتيه
    -0.79
     Perſ
    -0.77
    LookAnd
    -0.77
     Мексичка
    -0.76
    POSITIVE LOGITS
    }());
    0.43
     ημέ
    0.37
     UPON
    0.36
     upon
    0.35
     utilizarse
    0.35
     asupra
    0.34
     Upon
    0.34
    maktadır
    0.34
     znacz
    0.34
    rxjs
    0.34
    Activations Density 0.914%

    No Known Activations