© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4824
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to finance and legal concepts

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

    Code snippets and uncommon words

    np_acts-logits-general · gemini-2.0-flash

    financial transactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PRNewswire
    -0.60
     marketing
    -0.59
     programmed
    -0.56
    StoredProcedure
    -0.54
    RenderAtEndOf
    -0.54
     coaching
    -0.53
     transactional
    -0.52
     commissioning
    -0.50
    #+#
    -0.50
     Inter
    -0.49
    POSITIVE LOGITS
    RTEE
    0.66
    medriver
    0.56
    createTextNode
    0.55
    Rüyada
    0.54
    ญา
    0.53
     nudity
    0.51
    endphp
    0.51
    XMLSchema
    0.51
    jewództ
    0.51
     déplacements
    0.50
    Activations Density 1.085%

    No Known Activations