Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14331
    Prev
    Next
    INDEX
    Explanations

    discussions of methodology and analysis in research contexts

    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
     للاسماء
    -0.47
     وتسجيلات
    -0.47
     Congrats
    -0.46
     autorytatywna
    -0.46
     VIAF
    -0.46
     congrats
    -0.45
    </em>
    -0.45
    WriteTagHelper
    -0.44
    ỏa
    -0.43
    VIAF
    -0.42
    POSITIVE LOGITS
     discussion
    1.33
     Section
    1.20
    discussion
    1.19
    Section
    1.17
     section
    1.15
     Sections
    1.14
     subsections
    1.12
    Sections
    1.11
     discuss
    1.11
     sections
    1.10
    Activations Density 1.494%

    No Known Activations