© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 11423
    Prev
    Next
    INDEX
    Explanations

    coding commands and operations involving string manipulation and concatenation

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

    Code related to string concatenation or appending

    np_acts-logits-general · gemini-2.0-flash

    operators and string concatenation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.60
    formik
    -0.42
    Personensuche
    -0.41
    )}_{
    -0.39
     Савезне
    -0.35
     metav
    -0.32
    #
    -0.32
    phoric
    -0.32
     SAD
    -0.32
    bibitem
    -0.31
    POSITIVE LOGITS
    PerformLayout
    0.63
    endphp
    0.61
    ftagPool
    0.61
    UnusedPrivate
    0.60
    enterOuterAlt
    0.57
    Append
    0.56
    setVerticalGroup
    0.54
    putchar
    0.50
     AssemblyTitle
    0.49
     příslu
    0.48
    Activations Density 0.605%

    No Known Activations