© 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. 27-GEMMASCOPE-RES-16K
    6. 10059
    Prev
    Next
    INDEX
    Explanations

    technical terms and mathematical symbols related to formal expressions and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſicht
    -0.80
    +#+#
    -0.80
    parsedMessage
    -0.79
    URLException
    -0.75
    #+#
    -0.74
    <unused68>
    -0.73
    <unused52>
    -0.73
    <unused21>
    -0.72
    [@BOS@]
    -0.71
     fubject
    -0.71
    POSITIVE LOGITS
     justicia
    0.39
      
    0.39
     publicação
    0.38
     justiça
    0.37
     it
    0.36
     lietu
    0.35
     inscrição
    0.35
     tirantes
    0.35
     muerto
    0.35
     disparu
    0.34
    Activations Density 0.735%

    No Known Activations