© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102934
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "concat" and its variations related to string manipulation in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    concat with parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.51
     UserProfile
    -0.50
    viewDidLoad
    -0.48
    MemoryWarning
    -0.47
    SError
    -0.46
    YR
    -0.46
    ]");
    -0.44
     Rukh
    -0.44
     UserModel
    -0.43
     опо
    -0.43
    POSITIVE LOGITS
    concat
    1.34
     concat
    1.19
    Concat
    1.13
     concatenation
    0.91
    concatenate
    0.86
    concaten
    0.82
     concaten
    0.78
     concatenate
    0.77
    prepend
    0.67
    EndContext
    0.66
    Activations Density 0.013%

    No Known Activations