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. 24-GEMMASCOPE-RES-16K
    6. 4337
    Prev
    Next
    INDEX
    Explanations

    important financial and economic terms related to market dynamics

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

    Business or financial jargon

    np_acts-logits-general · gemini-2.0-flash

    business and finance entities

    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
     getItemId
    -0.60
    Kinds
    -0.58
    MetaObject
    -0.57
     صوتيه
    -0.56
    haup
    -0.55
    VersionUID
    -0.55
    wpdb
    -0.52
     Prose
    -0.52
    (!__
    -0.52
    archiviato
    -0.51
    POSITIVE LOGITS
     EMEA
    0.77
     jurisdictions
    0.76
     bespoke
    0.69
     structuring
    0.68
     onshore
    0.65
     unrivalled
    0.61
     Asia
    0.61
     ESG
    0.59
     deal
    0.57
     Struct
    0.57
    Activations Density 0.193%

    No Known Activations