Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 8393
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical processes and compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beſch
    -0.56
     MainAxisSize
    -0.55
    SBATCH
    -0.54
    occas
    -0.54
    advantages
    -0.53
    maximal
    -0.52
    куртка
    -0.52
     beſti
    -0.51
    GRANTED
    -0.51
    spania
    -0.51
    POSITIVE LOGITS
     chemical
    0.94
     Chemical
    0.92
     Chemistry
    0.89
    Chemical
    0.86
     chemistry
    0.85
     chemist
    0.83
    Chemistry
    0.82
    chemical
    0.81
     chemicals
    0.77
     chemists
    0.76
    Activations Density 0.193%

    No Known Activations