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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 28021
    Prev
    Next
    INDEX
    Explanations

    instructions related to installation tasks

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

    Mentions of installation or installing (words and forms referring to installing, installed, or installation).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     disambiguazione
    -0.40
    wezen
    -0.38
    homonymie
    -0.35
     ©️
    -0.35
    GRAPHICAL
    -0.32
     táctil
    -0.31
    Tikang
    -0.31
     ProtoMessage
    -0.31
    łaszcza
    -0.30
    rawDesc
    -0.30
    POSITIVE LOGITS
    contractor
    0.63
    professionals
    0.58
     trow
    0.54
     DIY
    0.54
     contractor
    0.53
     drywall
    0.52
     հղումներ
    0.51
     contractors
    0.51
     installers
    0.50
    WPA
    0.49
    Activations Density 0.011%

    No Known Activations