© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15345
    Prev
    Next
    INDEX
    Explanations

    references to the concept of attachment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getColumnIndex
    -0.85
    rocco
    -0.74
    imageio
    -0.69
     Rama
    -0.69
    Rama
    -0.68
     alman
    -0.68
     colspan
    -0.66
     GenerationType
    -0.66
    Kore
    -0.65
    awtextra
    -0.65
    POSITIVE LOGITS
     attachment
    2.34
     attached
    2.32
     attach
    2.27
     Attach
    2.22
     ATTACH
    2.22
     attachments
    2.19
     attaches
    2.17
     attaching
    2.16
     Attached
    2.14
    attach
    2.14
    Activations Density 0.069%

    No Known Activations