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. 31-GEMMASCOPE-RES-16K
    6. 15663
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their structural characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Chemical compounds containing "ring"

    np_acts-logits-general · gemini-2.0-flash

    isoquinoline ring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.53
    SBATCH
    -0.45
    存于互联网档案馆
    -0.44
    reportWebVitals
    -0.42
    RenderAtEndOf
    -0.41
     brach
    -0.39
    UrlResolution
    -0.39
    postsleuth
    -0.38
     takut
    -0.36
     BoxFit
    -0.36
    POSITIVE LOGITS
     ring
    0.76
     Ring
    0.63
    Ring
    0.62
     rings
    0.62
     anillo
    0.58
     RING
    0.54
     Rings
    0.50
     fused
    0.49
    ring
    0.49
    Rings
    0.47
    Activations Density 0.443%

    No Known Activations