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. 5-GEMMASCOPE-RES-16K
    6. 13454
    Prev
    Next
    INDEX
    Explanations

    references to configuration settings for software or libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.66
    awtextra
    -0.53
    tagHelper
    -0.48
     gen
    -0.44
    SuppressWarnings
    -0.43
     who
    -0.43
     ViewHolder
    -0.43
    <tr>
    -0.41
    jspx
    -0.41
     
    -0.41
    POSITIVE LOGITS
    migrationBuilder
    1.88
    AndEndTag
    1.80
     Illuminate
    1.57
     iParam
    1.57
    #+#
    1.50
    iParam
    1.35
    Illuminate
    1.30
    :+:
    1.19
     Мексичка
    1.04
     iprot
    1.03
    Activations Density 0.008%

    No Known Activations