© 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 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. 19008
    Prev
    Next
    INDEX
    Explanations

    phrases relating to the act of raising or increasing something, particularly bills or costs

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

    put up or erected

    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
    DebuggerNonUser
    -0.57
     useAppContext
    -0.54
    bcryptjs
    -0.48
    bcrypt
    -0.47
     CWE
    -0.45
    例句
    -0.45
    ContentAlignment
    -0.44
    gypte
    -0.43
     "..\..\
    -0.43
    RotationOrder
    -0.43
    POSITIVE LOGITS
     put
    0.65
     erected
    0.60
     Put
    0.57
    Put
    0.55
     up
    0.54
     erect
    0.52
     tall
    0.52
     erecting
    0.52
     putting
    0.51
     PUT
    0.50
    Activations Density 0.008%

    No Known Activations