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. 11747
    Prev
    Next
    INDEX
    Explanations

    song titles and lyrics references

    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
     linkovi
    -0.54
     оригіналу
    -0.54
     كومونز
    -0.49
    ьаж
    -0.48
     становника
    -0.48
     again
    -0.47
    سمبر
    -0.47
    Vanjske
    -0.46
    asztal
    -0.45
    แห่ง
    -0.44
    POSITIVE LOGITS
    出版年
    0.81
     myſelf
    0.62
    IndentedString
    0.61
     thermoc
    0.59
     MonoBehaviour
    0.58
     Jefus
    0.58
     Majefty
    0.56
    __":
    0.55
    WebVitals
    0.55
     pleaſure
    0.54
    Activations Density 0.122%

    No Known Activations