© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2809
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to financial transactions and the distribution of funds

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

    phrases describing money being transferred, distributed, or used for specific purposes.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*")]
    -0.57
     سكانية
    -0.44
    GTCX
    -0.43
    Handlung
    -0.42
     xảy
    -0.42
     lenker
    -0.42
    Гео
    -0.42
    TabIndex
    -0.40
     otomatig
    -0.39
    dolu
    -0.37
    POSITIVE LOGITS
     earmarked
    0.67
     expended
    0.67
     dépens
    0.66
     przeznac
    0.63
     donated
    0.63
     allocated
    0.63
     spent
    0.62
     confiscated
    0.61
     deposited
    0.61
     accumulated
    0.60
    Activations Density 0.599%

    No Known Activations