© 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. 28-GEMMASCOPE-RES-16K
    11. 4106
    Prev
    Next
    INDEX
    Explanations

    technical or structured data related to software and system errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or file paths

    np_acts-logits-general · gemini-2.0-flash

    CPU and E-Suite validator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.78
     zwiſchen
    -0.73
    principalColumn
    -0.70
    iſchen
    -0.69
    <unused17>
    -0.69
    <pad>
    -0.69
    <unused20>
    -0.69
    <unused8>
    -0.69
    iſche
    -0.69
    <unused16>
    -0.68
    POSITIVE LOGITS
     "
    0.30
     Even
    0.30
    Even
    0.29
     even
    0.29
     \"
    0.29
     palo
    0.28
     Corte
    0.27
     defaultstate
    0.26
     engineering
    0.26
     EVEN
    0.25
    Activations Density 0.723%

    No Known Activations