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. 4359
    Prev
    Next
    INDEX
    Explanations

    financial terms and references related to corporate actions and outcomes

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

    company leadership

    np_acts-logits-general · gemini-2.0-flash

    executives and shareholders

    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
     Vereine
    -0.45
    XtraGrid
    -0.43
     препратки
    -0.43
    uč
    -0.42
    RequiresApi
    -0.41
    vány
    -0.41
    bieter
    -0.40
     सत्यापित
    -0.40
     minutter
    -0.40
     svolge
    -0.40
    POSITIVE LOGITS
     CEO
    1.60
     executives
    1.48
     shareholders
    1.42
    CEO
    1.40
     shareholder
    1.31
     ceo
    1.30
     CEOs
    1.26
     management
    1.25
     Executives
    1.20
     CFO
    1.18
    Activations Density 0.442%

    No Known Activations