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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 52920
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to ion channels and electrical conductance properties

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

    ion channel electrical activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.58
     project
    -0.48
     case
    -0.47
     cast
    -0.46
     "
    -0.46
     W
    -0.46
     Adler
    -0.45
     w
    -0.45
     (
    -0.44
     ра
    -0.44
    POSITIVE LOGITS
    WebVitals
    1.14
    SharedDtor
    1.13
     дописавши
    1.09
    invokeLater
    1.05
    rungsseite
    1.05
    LookAnd
    1.05
     للمعارف
    1.04
     <<<<<<<<<<<<<<
    1.02
    脚注の使い方
    1.02
     propOrder
    1.02
    Activations Density 1.010%

    No Known Activations