© 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. 0-GEMMASCOPE-RES-16K
    11. 2357
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "were"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Geſch
    -1.04
    <unused52>
    -1.01
    <unused16>
    -1.01
    [@BOS@]
    -1.00
    <unused74>
    -1.00
    <unused41>
    -1.00
    <unused68>
    -1.00
    <unused51>
    -1.00
    <unused3>
    -1.00
    <unused28>
    -1.00
    POSITIVE LOGITS
     are
    1.47
     were
    1.38
     sont
    1.36
     são
    1.06
     sind
    1.05
     sono
    1.05
    were
    0.94
     waren
    0.94
     zijn
    0.93
     są
    0.92
    Activations Density 0.639%

    No Known Activations