© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 10918
    Prev
    Next
    INDEX
    Explanations

    themes related to financial priorities and issues surrounding debt management

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

    Percentages or proportions

    np_acts-logits-general · gemini-2.0-flash

    percentages, proportions, or majority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.61
     poffe
    -0.53
    exitRule
    -0.53
    ⤹
    -0.52
     pleaſure
    -0.52
     ſte
    -0.52
    IntentFilter
    -0.50
     myſelf
    -0.50
     ſei
    -0.50
    InsertCommand
    -0.50
    POSITIVE LOGITS
     majority
    1.18
     nearly
    1.11
     Nearly
    1.03
    Nearly
    1.00
     almost
    0.98
    Majority
    0.97
    majority
    0.96
     half
    0.96
     approximately
    0.93
     percentage
    0.92
    Activations Density 1.219%

    No Known Activations