© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 116537
    Prev
    Next
    INDEX
    Explanations

    specific actions and concepts related to problem-solving and decision-making processes

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

    how to achieve outcomes

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects action/process verbs (often -ing forms) that describe methods, tasks, or activities like determining, defining, developing, describing, proving, and achieving.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    internalType
    -0.47
    UserScript
    -0.30
    ٔ
    -0.28
    propTypes
    -0.28
    †
    -0.28
    WriteBarrier
    -0.28
     
    -0.27
     Qaraldi
    -0.27
    …
    -0.26
     Cer
    -0.26
    POSITIVE LOGITS
    RenderAtEndOf
    0.77
    Personendaten
    0.73
     myſelf
    0.65
    ſelben
    0.65
     queſta
    0.65
     wiſſen
    0.64
     ſoll
    0.64
    ⟬
    0.63
     EconPapers
    0.63
     ſehr
    0.62
    Activations Density 0.207%

    No Known Activations