© 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. 15855
    Prev
    Next
    INDEX
    Explanations

    names of individuals or characters

    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
    AddTagHelper
    -0.89
     itſelf
    -0.73
    yntaxException
    -0.70
     cdti
    -0.70
    principalColumn
    -0.70
     Filho
    -0.69
     hjelp
    -0.68
     tilgjenge
    -0.64
    Gizmos
    -0.64
     contextLoads
    -0.64
    POSITIVE LOGITS
     Max
    0.60
    esco
    0.57
    ("%.
    0.56
    المكان
    0.52
    /-/
    0.51
     Lett
    0.50
    >*
    0.50
    вен
    0.49
    tead
    0.49
    *,
    0.48
    Activations Density 0.087%

    No Known Activations