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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8737
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to shape and geometry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewUrlParser
    -0.54
     colorir
    -0.52
    },[])
    -0.49
     CreateTagHelper
    -0.45
     Nội
    -0.43
    ChildScrollView
    -0.43
    diali
    -0.42
     noDo
    -0.42
    ریم
    -0.42
    poň
    -0.42
    POSITIVE LOGITS
     rectangular
    1.19
     oval
    1.17
     triangular
    1.09
     oblong
    1.05
     round
    1.05
     square
    1.04
     trapez
    1.02
     rounded
    1.00
     rectangle
    1.00
    rectangular
    0.99
    Activations Density 0.877%

    No Known Activations