© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29202
    Prev
    Next
    INDEX
    Explanations

    occurrences of the token "<bos>", which likely indicates the start of a new section or paragraph

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

    confirmation after brief pause

    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
     ResourceManager
    -0.54
    uarts
    -0.52
     Reverso
    -0.50
    zzleHttp
    -0.50
     <>",
    -0.49
    InvalidProtocol
    -0.49
    AddTagHelper
    -0.49
    >>()
    -0.48
     Wikimedijinoj
    -0.48
     [*]
    -0.47
    POSITIVE LOGITS
     ovviamente
    1.88
     obviamente
    1.75
     obviously
    1.74
    obviously
    1.73
     oczywiście
    1.68
     évidemment
    1.65
     natürlich
    1.53
     Obviously
    1.52
     natuurlijk
    1.52
     ofc
    1.48
    Activations Density 0.228%

    No Known Activations