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. 4577
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in the entertainment industry, particularly in film production and script development

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

    startups or company funding

    np_acts-logits-general · gemini-2.0-flash

    startups and investments

    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
     يتيمه
    -0.68
    ErrUnexpectedEOF
    -0.62
    BeginContext
    -0.55
    TagMode
    -0.53
    FormTagHelper
    -0.52
    Память
    -0.50
     spool
    -0.49
     تضيفلها
    -0.49
    athion
    -0.48
     misure
    -0.48
    POSITIVE LOGITS
     startup
    1.34
     founders
    1.26
     startups
    1.25
     Startup
    1.18
    startup
    1.12
     Startups
    1.09
     venture
    1.06
    Startup
    1.05
     Founders
    1.02
     bootstra
    1.01
    Activations Density 0.267%

    No Known Activations