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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3411
    Prev
    Next
    INDEX
    Explanations

    frequent occurrences of the word "de" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faſt
    -0.66
     raiſ
    -0.63
     pleaſure
    -0.60
     slutt
    -0.59
     chrétien
    -0.58
     ſtand
    -0.56
     ainfi
    -0.56
     ſever
    -0.56
     ſta
    -0.54
    ſelf
    -0.54
    POSITIVE LOGITS
     de
    1.34
     De
    0.91
     of
    0.91
     di
    0.88
    De
    0.86
     OF
    0.79
     DE
    0.78
     von
    0.75
    ของ
    0.75
     де
    0.72
    Activations Density 0.069%

    No Known Activations