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. 9-GEMMASCOPE-RES-16K
    6. 15191
    Prev
    Next
    INDEX
    Explanations

    discussion around preferences and societal norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sculptured
    -0.64
     noOf
    -0.64
     !!!
    -0.64
    maktadır
    -0.63
    omiast
    -0.61
    ="#"><
    -0.59
     می‌باشد
    -0.59
    又は
    -0.58
     již
    -0.58
     אשר
    -0.57
    POSITIVE LOGITS
     weirdly
    1.00
     vaguely
    0.97
     goddamn
    0.93
     whatnot
    0.91
     iirc
    0.89
     shitty
    0.89
     ostensibly
    0.85
     pretty
    0.83
     awkwardly
    0.82
     lemme
    0.82
    Activations Density 1.833%

    No Known Activations