© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 10729
    Prev
    Next
    INDEX
    Explanations

    characters and their relationships within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     messing
    -0.54
     gonna
    -0.53
     messed
    -0.49
     freakin
    -0.48
     just
    -0.48
     freaking
    -0.46
     kinda
    -0.45
     Really
    -0.42
     gotta
    -0.42
     REALLY
    -0.41
    POSITIVE LOGITS
     frequently
    0.73
     skillfully
    0.70
     skil
    0.69
     quickly
    0.68
    AddTagHelper
    0.68
     ModelExpression
    0.68
     queſta
    0.68
    StoryboardSegue
    0.68
    TagMode
    0.66
     mView
    0.66
    Activations Density 1.093%

    No Known Activations