Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 3795
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and their patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.96
    ]")]
    -0.88
    <unused21>
    -0.87
    <unused52>
    -0.87
    <unused68>
    -0.86
    <unused28>
    -0.86
    <unused16>
    -0.86
    </caption>
    -0.85
    <unused14>
    -0.85
    <unused8>
    -0.85
    POSITIVE LOGITS
     The
    0.59
    It
    0.56
    As
    0.53
    When
    0.52
     Although
    0.51
    Since
    0.51
    Although
    0.51
     As
    0.51
     When
    0.51
    This
    0.50
    Activations Density 0.878%

    No Known Activations