© 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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 66424
    Prev
    Next
    INDEX
    Explanations

    terms related to construction or building activities

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

    created or built structures

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Roskov
    -0.69
     getItemId
    -0.65
    Thompson
    -0.63
     kaarangay
    -0.61
    medriver
    -0.59
    Allison
    -0.59
    JsonHelper
    -0.59
    momix
    -0.58
    Thal
    -0.58
     Correspond
    -0.58
    POSITIVE LOGITS
     erected
    1.51
     erect
    1.38
     erecting
    1.35
     erection
    1.28
     Ere
    0.81
     erec
    0.71
    Ere
    0.68
     errichtet
    0.63
     constructed
    0.56
     erectile
    0.55
    Activations Density 0.005%

    No Known Activations