© 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. 15353
    Prev
    Next
    INDEX
    Explanations

    terms related to organ and optimization concepts in various contexts

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

    Followed by "-elle" or "ality"

    np_acts-logits-general · gemini-2.0-flash

    organelle, minimality, organophosphates

    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
     []:
    -0.57
    ure
    -0.54
    ATURE
    -0.47
    bit
    -0.43
    ures
    -0.43
    ature
    -0.43
    sel
    -0.41
    క్ష
    -0.41
    olan
    -0.41
    tive
    -0.40
    POSITIVE LOGITS
    XmlAccessType
    0.84
     purpoſe
    0.81
    AddTagHelper
    0.81
    Дереккөздер
    0.79
    istically
    0.77
     itſelf
    0.76
     uſed
    0.76
    ContentAlignment
    0.72
     ostavi
    0.71
     ſtate
    0.71
    Activations Density 0.223%

    No Known Activations