© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 12020
    Prev
    Next
    INDEX
    Explanations

    terms indicating success or failure, particularly in legal or medical contexts

    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
     initComponents
    -0.56
    ंदीखरीदारी
    -0.47
     Infórmanos
    -0.45
    Autoritní
    -0.42
    actionMode
    -0.40
    DOCTYPE
    -0.40
    IntoConstraints
    -0.39
    StructEnd
    -0.38
     Fine
    -0.37
    期刊论文
    -0.36
    POSITIVE LOGITS
    full
    2.20
    ful
    2.19
    fulness
    2.08
    FUL
    1.98
    fully
    1.91
    FULL
    1.79
     full
    1.70
     ful
    1.58
    fuls
    1.54
    Full
    1.53
    Activations Density 0.265%

    No Known Activations