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. 1011
    Prev
    Next
    INDEX
    Explanations

    details related to product condition and packaging in commercial descriptions

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

    item packaging

    np_acts-logits-general · gemini-2.0-flash

    packaging and related containers

    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
    ExtendWith
    -0.66
    LookAnd
    -0.61
    MIDDLEWARE
    -0.59
     gyhoeddwyd
    -0.59
     disambiguazione
    -0.58
    \|_{\
    -0.57
    GRANTED
    -0.57
     فريبيس
    -0.56
     HttpNotFound
    -0.56
    DeleteBehavior
    -0.55
    POSITIVE LOGITS
     packaging
    2.06
     Packaging
    1.72
    packaging
    1.60
     package
    1.59
    Packaging
    1.58
     packing
    1.54
     packages
    1.47
     packaged
    1.42
     PACK
    1.36
     pack
    1.35
    Activations Density 0.158%

    No Known Activations