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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12790
    Prev
    Next
    INDEX
    Explanations

    constructs and terminology related to programming and object-oriented design, particularly in C++

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.54
     يتيمه
    -0.52
    <_>
    -0.48
     TÉCN
    -0.47
     poveznice
    -0.45
     raggiung
    -0.44
     HFILL
    -0.44
     TECHNI
    -0.44
     Cruces
    -0.43
     vPvB
    -0.43
    POSITIVE LOGITS
    getDescriptor
    0.43
    detectChanges
    0.43
     ModelExpression
    0.42
    setPreferred
    0.41
     astore
    0.40
     CWE
    0.39
    sizeCache
    0.38
    🇶
    0.37
    UIControlState
    0.37
    PickerController
    0.36
    Activations Density 0.204%

    No Known Activations