© 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
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 14310
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Indium" and related programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IA
    -1.24
     IB
    -1.24
     IC
    -1.20
     IP
    -1.20
     IG
    -1.15
     IR
    -1.13
     IM
    -1.10
     IK
    -1.08
     IL
    -1.05
     IH
    -1.05
    POSITIVE LOGITS
    classnames
    0.56
    is
    0.56
    Inc
    0.50
    if
    0.47
    numerusform
    0.47
    id
    0.47
    i
    0.46
    Important
    0.46
    Ing
    0.46
    AxisAlignment
    0.46
    Activations Density 0.419%

    No Known Activations