© 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. 2-GEMMASCOPE-RES-16K
    11. 3068
    Prev
    Next
    INDEX
    Explanations

    references to affordability and financial struggles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelSerializer
    -0.56
     viewType
    -0.42
     bel
    -0.40
     Hey
    -0.40
     bell
    -0.40
     proper
    -0.38
    WithMany
    -0.37
     consisting
    -0.37
     train
    -0.36
     outer
    -0.35
    POSITIVE LOGITS
     duo
    0.71
     EconPapers
    0.63
    expandindo
    0.58
    duo
    0.57
    Duo
    0.57
     trio
    0.56
    tangentMode
    0.55
    tagHelperRunner
    0.54
     Duo
    0.54
    www
    0.54
    Activations Density 0.160%

    No Known Activations