Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 3197
    Prev
    Next
    INDEX
    Explanations

    the term "raw" and its variations related to materials and processes

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

    "raw"

    np_acts-logits-general · gemini-2.0-flash

    raw string, raw materials, Rawk, Rawhide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GetEnumerator
    -0.83
     CreateTagHelper
    -0.82
    matchCondition
    -0.80
     Majefty
    -0.78
     myſelf
    -0.76
     Monfieur
    -0.75
    enderror
    -0.73
     nakalista
    -0.73
     disponibilités
    -0.71
     pleaſure
    -0.70
    POSITIVE LOGITS
     Raw
    1.37
     raw
    1.24
    Raw
    1.19
     RAW
    1.18
    RAW
    1.06
    raw
    1.00
     materials
    0.79
    rawData
    0.77
     material
    0.74
    getRaw
    0.73
    Activations Density 0.047%

    No Known Activations