© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8861
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "express" and its related forms

    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
    parsedMessage
    -1.09
     autorytatywna
    -1.02
     myſelf
    -0.98
    <pad>
    -0.98
    <unused68>
    -0.97
    [@BOS@]
    -0.97
    <unused28>
    -0.96
    <unused41>
    -0.96
    <unused23>
    -0.96
    <unused8>
    -0.96
    POSITIVE LOGITS
     express
    1.13
     expression
    1.03
     expressing
    1.02
     Express
    0.94
     expressed
    0.92
     Expression
    0.91
    Expression
    0.90
     expresses
    0.88
    Express
    0.81
    expression
    0.81
    Activations Density 0.362%

    No Known Activations