© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15170
    Prev
    Next
    INDEX
    Explanations

    instances of the characters '{' and '}' which are commonly used for defining blocks of code or statements in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.83
     CreateTagHelper
    -0.79
    Chham
    -0.69
    enterOuterAlt
    -0.68
     Efq
    -0.67
    ConstraintMaker
    -0.66
     intptr
    -0.65
    Šaltiniai
    -0.65
    numerusform
    -0.65
     igång
    -0.64
    POSITIVE LOGITS
    modelBuilder
    0.77
    WindowConstants
    0.61
    complexType
    0.53
     VIDEOTAPE
    0.52
     peran
    0.52
     виправивши
    0.50
    DebuggerNonUser
    0.50
    <bos>
    0.50
     perio
    0.50
    CppMethod
    0.50
    Activations Density 0.021%

    No Known Activations