Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 15578
    Prev
    Next
    INDEX
    Explanations

    concepts related to financial and administrative themes

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

    following types of business/services

    np_acts-logits-general · gemini-2.0-flash

    financial services and life events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     avoient
    -0.94
     ainfi
    -0.86
     leaſt
    -0.83
     étoient
    -0.82
     auroit
    -0.82
     feroit
    -0.81
     plufieurs
    -0.81
     whoſe
    -0.80
     purpoſe
    -0.77
     enfans
    -0.77
    POSITIVE LOGITS
     thing
    1.26
     stuff
    1.17
     things
    0.90
     thingy
    0.87
     guy
    0.83
     issues
    0.76
     crap
    0.74
     THING
    0.73
     Sachen
    0.69
     issue
    0.69
    Activations Density 0.443%

    No Known Activations