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. 18-GEMMASCOPE-RES-16K
    6. 10471
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting structures in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -1.14
     greateſt
    -1.10
     pleaſure
    -1.10
     itſelf
    -1.10
     myſelf
    -1.06
     Reſ
    -1.05
     houſe
    -1.04
     reaſon
    -1.01
     uſ
    -1.00
    ſelves
    -0.99
    POSITIVE LOGITS
    ↵↵
    1.08
    ↵↵↵
    0.80
     The
    0.76
     (
    0.65
     “
    0.65
    </strong>
    0.64
     "
    0.63
    ↵↵↵↵
    0.63
    ↵
    0.62
     Similarly
    0.62
    Activations Density 0.627%

    No Known Activations