© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9785
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to computer systems and programming

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

    Code, equations, or other technical content

    np_acts-logits-general · gemini-2.0-flash

    introductions to specific components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.94
     ſind
    -0.92
     WebDriverWait
    -0.91
    الدراسه
    -0.89
     rospy
    -0.89
    BagConstraints
    -0.86
     Waray
    -0.85
    ſelves
    -0.85
     AttributeSet
    -0.82
    URLException
    -0.82
    POSITIVE LOGITS
    <eos>
    1.19
    ↵↵
    0.94
    ↵
    0.81
    ↵↵↵
    0.80
    ↵↵↵↵
    0.79
    ↵↵↵↵↵
    0.64
    ())));
    0.63
     I
    0.62
    }}
    0.62
     class
    0.61
    Activations Density 0.266%

    No Known Activations