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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 8892
    Prev
    Next
    INDEX
    Explanations

    terms related to financial services and accounting practices

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

    Follows certain adjectives/verbs

    np_acts-logits-general · gemini-2.0-flash

    experience, thanks, lovely, look, experienced, work, disgrace, advocate, areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flavorful
    -1.26
    Neighbors
    -1.24
     neighborhood
    -1.24
     neighborhoods
    -1.23
    AVOR
    -1.23
     honors
    -1.19
    FAVOR
    -1.19
     favorite
    -1.19
     colors
    -1.18
     neighbors
    -1.16
    POSITIVE LOGITS
    Whilst
    2.06
     Whilst
    1.98
     whilst
    1.79
    initialise
    1.73
     organisers
    1.52
     realising
    1.52
     realise
    1.50
     recognised
    1.50
     Organisations
    1.50
     recognisable
    1.50
    Activations Density 5.321%

    No Known Activations