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. 18-GEMMASCOPE-RES-16K
    6. 8684
    Prev
    Next
    INDEX
    Explanations

    references to events and conferences, particularly related to technology and awards

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

    preceding names of events

    np_acts-logits-general · gemini-2.0-flash

    conferences, festivals, conventions

    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
    TagHelper
    -0.64
    出版年
    -0.64
    HasAnnotation
    -0.61
     متعلقه
    -0.55
     EnglishChoose
    -0.54
    LayoutStyle
    -0.54
     saites
    -0.53
     roul
    -0.52
    žad
    -0.52
    WebElementEntity
    -0.51
    POSITIVE LOGITS
     conferences
    1.04
     conference
    1.00
     convention
    0.89
     festival
    0.86
     Conference
    0.86
     Festival
    0.83
     conventions
    0.82
    fest
    0.81
    conference
    0.80
    Conference
    0.78
    Activations Density 0.199%

    No Known Activations