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. 16-GEMMASCOPE-RES-16K
    6. 15943
    Prev
    Next
    INDEX
    Explanations

    terms related to hydrochemical processes or compounds

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

    "hydro" and related terms

    np_acts-logits-general · gemini-2.0-flash

    hydro- prefix with chemical or scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    postIndex
    -0.73
    Rüyada
    -0.71
     cholesterol
    -0.71
     Margo
    -0.70
     astronomers
    -0.70
     astronomer
    -0.67
     Zoro
    -0.67
     Cholesterol
    -0.66
     Bohemia
    -0.66
     Atari
    -0.66
    POSITIVE LOGITS
     hyd
    1.02
    Hyd
    0.99
     Hyd
    0.96
    HYDRO
    0.83
     hydro
    0.82
    hydra
    0.81
     Hydro
    0.80
    hyd
    0.80
    hydr
    0.80
     Hyde
    0.80
    Activations Density 0.213%

    No Known Activations