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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 8422
    Prev
    Next
    INDEX
    Explanations

    phrases related to laying or establishing a foundational basis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ProcessEvent
    -0.42
    emptyList
    -0.40
     kotlinx
    -0.36
    PullParser
    -0.35
    böz
    -0.35
    ricultural
    -0.34
     viciss
    -0.34
     kring
    -0.34
    ActionCreators
    -0.34
    TAGE
    -0.33
    POSITIVE LOGITS
     foundation
    1.73
     foundations
    1.58
    foundation
    1.40
     Foundations
    1.39
     Foundation
    1.34
    Foundation
    1.34
     FOUNDATION
    1.33
    Foundations
    1.30
     foundational
    1.24
     Grundlage
    1.19
    Activations Density 0.351%

    No Known Activations