© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11263
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pendenti
    -0.41
     bankası
    -0.41
    Properties
    -0.41
     Properties
    -0.39
    grafos
    -0.38
     nasional
    -0.38
     kas
    -0.37
     инстру
    -0.37
    properties
    -0.36
     chirurgie
    -0.36
    POSITIVE LOGITS
     كومونز
    0.98
    ISupport
    0.92
     BoxDecoration
    0.90
    parsedMessage
    0.90
     GenerationType
    0.89
    TagHelper
    0.88
    +:+
    0.87
     للاسماء
    0.86
    enumi
    0.86
     للمعارف
    0.84
    Activations Density 2.863%

    No Known Activations