Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 38718
    Prev
    Next
    INDEX
    Explanations

    code constructs and programming elements related to data management and state within a software context

    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
     iſt
    -0.99
    AddTagHelper
    -0.97
     Majefty
    -0.96
     Efq
    -0.96
     doubtnut
    -0.96
    Portail
    -0.93
    ✨:
    -0.93
    neſs
    -0.92
     سكانية
    -0.92
     whoſe
    -0.92
    POSITIVE LOGITS
     is
    0.47
    ngdoc
    0.45
     get
    0.43
     r
    0.43
    pre
    0.42
     are
    0.41
    ;
    0.41
     
    0.41
     prí
    0.41
     $
    0.41
    Activations Density 0.005%

    No Known Activations