© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8178
    Prev
    Next
    INDEX
    Explanations

    references to attachment or connectedness of objects or systems

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

    "attach"

    np_acts-logits-general · gemini-2.0-flash

    attach to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thée
    -0.53
    Stro
    -0.47
     cellpadding
    -0.47
    addGap
    -0.46
     Stro
    -0.46
     gaps
    -0.42
    IBar
    -0.42
    eu
    -0.41
    netbeans
    -0.41
    boxShadow
    -0.41
    POSITIVE LOGITS
     attaching
    1.44
     attaches
    1.39
     Attach
    1.38
     attach
    1.36
     attachment
    1.35
     attachments
    1.30
    Attach
    1.30
     ATTACH
    1.29
    attach
    1.27
     attached
    1.26
    Activations Density 0.310%

    No Known Activations