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. 21-GEMMASCOPE-RES-16K
    6. 7525
    Prev
    Next
    INDEX
    Explanations

    email addresses and contact requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    Дереккөздер
    -0.72
     opérateur
    -0.59
     Porém
    -0.57
    脚注の使い方
    -0.57
    DockStyle
    -0.56
    ArgsConstructor
    -0.54
     doInBackground
    -0.54
    twimg
    -0.53
    TagMode
    -0.53
     Савезне
    -0.53
    POSITIVE LOGITS
     info
    1.61
    info
    1.41
     Info
    1.13
    Info
    1.01
     INFO
    1.01
    INFO
    0.99
     admin
    0.95
    contact
    0.86
     hello
    0.85
    admin
    0.84
    Activations Density 0.070%

    No Known Activations