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. 3-GEMMASCOPE-RES-16K
    6. 11041
    Prev
    Next
    INDEX
    Explanations

    instances of significant dates or temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.68
     okuyayım
    -0.67
    WriteBarrier
    -0.67
    MethodManager
    -0.65
    তথ্যসূত্র
    -0.61
    jelder
    -0.60
     ICollection
    -0.60
    Amicalement
    -0.59
    twimg
    -0.59
    miyorum
    -0.57
    POSITIVE LOGITS
    ftagPool
    0.72
    ="@+
    0.57
    expandindo
    0.56
    ########.
    0.55
     propOrder
    0.52
    recated
    0.52
    odils
    0.52
     estuaries
    0.48
     '{@
    0.47
    writeFieldEnd
    0.45
    Activations Density 0.226%

    No Known Activations