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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6118
    Prev
    Next
    INDEX
    Explanations

    references to memory addresses and pointers in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -0.59
     fédé
    -0.51
     canst
    -0.49
     scolaires
    -0.45
    iseite
    -0.44
    chieht
    -0.43
    sstil
    -0.43
    кухня
    -0.43
     touristique
    -0.42
    yych
    -0.41
    POSITIVE LOGITS
     &___
    0.86
    (&
    0.83
    WriteTagHelper
    0.72
    +#+#
    0.65
    脚注の使い方
    0.64
    setof
    0.59
     CreateTagHelper
    0.57
    :✨
    0.56
    (&_
    0.56
    >(&
    0.54
    Activations Density 0.074%

    No Known Activations