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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56564
    Prev
    Next
    INDEX
    Explanations

    punctuation and speech markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disponibilités
    -0.53
     themſelves
    -0.52
    DISPATCH
    -0.50
     pylint
    -0.50
     newBuilder
    -0.49
     calendriers
    -0.49
     myſelf
    -0.48
     Lode
    -0.48
     Conſ
    -0.48
    PointerException
    -0.48
    POSITIVE LOGITS
    🙅
    0.71
     CreateTagHelper
    0.61
     negativas
    0.59
    🚫
    0.59
    SharedDtor
    0.58
     rechazo
    0.57
     оригіналу
    0.55
    MessageTagHelper
    0.55
     prohibiting
    0.54
     rechazar
    0.53
    Activations Density 0.224%

    No Known Activations