© 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 - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1737
    Prev
    Next
    INDEX
    Explanations

    functions and methods related to object property manipulation in programming

    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
    AndEndTag
    -1.09
    NameInMap
    -1.07
     betweenstory
    -0.99
    ANTLR
    -0.92
    Personensuche
    -0.89
    ItemBackground
    -0.87
     дописавши
    -0.83
     للاسماء
    -0.83
    istoitu
    -0.82
     disambiguazione
    -0.81
    POSITIVE LOGITS
    defineProperty
    0.52
     among
    0.48
    memberOf
    0.45
     tableView
    0.42
    $\
    0.41
    Pro
    0.40
    only
    0.39
    ​
    0.39
    式
    0.39
    Cal
    0.38
    Activations Density 0.800%

    No Known Activations