© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13386
    Prev
    Next
    INDEX
    Explanations

    terms related to mitochondrial function and biology

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

    "Mit" or words starting with "Mit"

    np_acts-logits-general · gemini-2.0-flash

    mit/MIT in various contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     McGuire
    -0.65
     resourceCulture
    -0.60
     Milner
    -0.58
    expandindo
    -0.58
    ordano
    -0.55
     Bale
    -0.54
    сур
    -0.54
    rungsseite
    -0.54
    EMPLO
    -0.53
    λες
    -0.52
    POSITIVE LOGITS
     Mit
    1.06
    Mit
    1.03
     MIT
    0.98
     Mith
    0.89
     mit
    0.86
     Mits
    0.86
    mit
    0.80
     كومونز
    0.76
    Mitch
    0.74
     mittens
    0.73
    Activations Density 0.212%

    No Known Activations