© 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-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2322
    Prev
    Next
    INDEX
    Explanations

    references to film production details and character attributes in reviews or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nuanced
    -0.94
     incentiv
    -0.87
     Notably
    -0.84
     underwhelming
    -0.83
     blurry
    -0.81
     impactful
    -0.81
     Kontext
    -0.79
     microbiome
    -0.79
     leveraging
    -0.77
     curation
    -0.77
    POSITIVE LOGITS
     muß
    0.74
     mußten
    0.67
    faßt
    0.67
     Moslem
    0.64
     mußte
    0.59
     skall
    0.58
     daß
    0.56
     läßt
    0.54
     quelquefois
    0.51
     müßte
    0.50
    Activations Density 11.206%

    No Known Activations