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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 12503
    Prev
    Next
    INDEX
    Explanations

    critiques of character development and narrative quality in stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.60
     RSITY
    -0.58
    }}^{(
    -0.57
    iastical
    -0.55
     AsyncTask
    -0.51
    seteq
    -0.50
     HAST
    -0.50
    }}_{\
    -0.49
    UITableView
    -0.49
     المعيارى
    -0.49
    POSITIVE LOGITS
     reservations
    0.65
     negatives
    0.57
    OGND
    0.57
     flaws
    0.55
     positives
    0.54
    ียด
    0.52
     تضيفلها
    0.52
     reservation
    0.52
     apology
    0.51
     caveats
    0.50
    Activations Density 0.167%

    No Known Activations