© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 9802
    Prev
    Next
    INDEX
    Explanations

    adjectives that convey a sense of exceptional quality or beauty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.64
     AssemblyCulture
    -0.62
     paranoia
    -0.60
    GEBURTS
    -0.59
    hicles
    -0.58
     assholes
    -0.58
     crappy
    -0.58
    XmlAccessorType
    -0.56
     shitty
    -0.55
    igslist
    -0.54
    POSITIVE LOGITS
     astonishing
    2.06
     astounding
    1.98
     remarkable
    1.95
     stunning
    1.77
     asomb
    1.59
     breathtaking
    1.54
    stunning
    1.53
     impressive
    1.52
     extraordinary
    1.49
     Remark
    1.46
    Activations Density 0.193%

    No Known Activations