© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31588
    Prev
    Next
    INDEX
    Explanations

    structured pattern indicators in a report format

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

    code snippets and variables

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    -
    -0.52
    —
    -0.48
     je
    -0.46
    :
    -0.44
     —
    -0.44
     com
    -0.44
    com
    -0.43
     «
    -0.43
     Make
    -0.43
    Autriche
    -0.43
    POSITIVE LOGITS
     snippetHide
    0.85
     IBOutlet
    0.84
     utafitiHapana
    0.79
    CloseOperation
    0.79
    DataAnnotations
    0.79
     ujednoznacz
    0.78
     viewDidLoad
    0.77
     AttributeSet
    0.77
     sumpay
    0.75
     viewDid
    0.73
    Activations Density 0.025%

    No Known Activations