© 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. 35-GEMMASCOPE-RES-16K
    11. 6836
    Prev
    Next
    INDEX
    Explanations

    positive evaluations and descriptions of experiences related to pets and family life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leider
    -0.52
     невозможно
    -0.50
     must
    -0.50
     cannot
    -0.49
     ممکن
    -0.48
    どうしても
    -0.47
     incomplete
    -0.46
    must
    -0.46
     certain
    -0.45
     sometimes
    -0.45
    POSITIVE LOGITS
     thankfully
    1.05
     fortunately
    0.91
     problemlos
    0.84
     вполне
    0.83
     happily
    0.83
     gelukkig
    0.82
    Thankfully
    0.81
     luckily
    0.80
     plenty
    0.79
     perfectamente
    0.77
    Activations Density 1.069%

    No Known Activations