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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15959
    Prev
    Next
    INDEX
    Explanations

    identifiers and terms associated with sub-structures in programming or data organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     ligiloj
    -0.70
     ThemeData
    -0.58
     laço
    -0.57
    łoży
    -0.51
    ậy
    -0.51
    RTEX
    -0.51
    tagHelperRunner
    -0.50
    Odour
    -0.50
     setTime
    -0.50
     CreateTagHelper
    -0.49
    POSITIVE LOGITS
     Sub
    1.13
    Sub
    1.10
     SUB
    1.05
    sub
    1.01
     sub
    1.00
    SUB
    0.94
     getSub
    0.91
    getSub
    0.91
     subs
    0.75
     subdivision
    0.75
    Activations Density 0.142%

    No Known Activations