© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 107441
    Prev
    Next
    INDEX
    Explanations

    references to completion and preparation processes

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

    preparing and finalizing steps

    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
     ***!
    -0.53
    adaptiveStyles
    -0.50
    SpringBootTest
    -0.50
     StringTokenizer
    -0.49
     MainAxisSize
    -0.49
    XmlAccessType
    -0.48
    LookAnd
    -0.47
    chaleco
    -0.47
    capture
    -0.47
     interesar
    -0.45
    POSITIVE LOGITS
     preparations
    0.78
     preparing
    0.64
     preparation
    0.63
     prepara
    0.62
     Preparations
    0.60
    prepar
    0.57
    Prepar
    0.54
     preparatory
    0.53
     prepare
    0.52
     preparar
    0.52
    Activations Density 0.057%

    No Known Activations