© 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. 9-GEMMASCOPE-RES-131K
    6. 17612
    Prev
    Next
    INDEX
    Explanations

    keywords related to popularity and success in various contexts

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

    excellence and deliverables

    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
     propOrder
    -0.61
     يتيمه
    -0.59
    DockStyle
    -0.50
     springfox
    -0.48
    Xna
    -0.47
    ImageContext
    -0.47
    Injector
    -0.46
     BoxDecoration
    -0.45
     CanadaChoose
    -0.45
    enumi
    -0.45
    POSITIVE LOGITS
     greatness
    1.43
     grandeza
    0.93
    ardom
    0.82
     grandeur
    0.72
    featureID
    0.66
    HasForeignKey
    0.54
     greats
    0.53
    itability
    0.52
    rapment
    0.47
     magnificence
    0.46
    Activations Density 0.005%

    No Known Activations